Dissociable neural representations of reinforcement and belief prediction errors underlie strategic learning.

PubMed

Zhu, Lusha; Mathewson, Kyle E; Hsu, Ming

2012-01-31

Decision-making in the presence of other competitive intelligent agents is fundamental for social and economic behavior. Such decisions require agents to behave strategically, where in addition to learning about the rewards and punishments available in the environment, they also need to anticipate and respond to actions of others competing for the same rewards. However, whereas we know much about strategic learning at both theoretical and behavioral levels, we know relatively little about the underlying neural mechanisms. Here, we show using a multi-strategy competitive learning paradigm that strategic choices can be characterized by extending the reinforcement learning (RL) framework to incorporate agents' beliefs about the actions of their opponents. Furthermore, using this characterization to generate putative internal values, we used model-based functional magnetic resonance imaging to investigate neural computations underlying strategic learning. We found that the distinct notions of prediction errors derived from our computational model are processed in a partially overlapping but distinct set of brain regions. Specifically, we found that the RL prediction error was correlated with activity in the ventral striatum. In contrast, activity in the ventral striatum, as well as the rostral anterior cingulate (rACC), was correlated with a previously uncharacterized belief-based prediction error. Furthermore, activity in rACC reflected individual differences in degree of engagement in belief learning. These results suggest a model of strategic behavior where learning arises from interaction of dissociable reinforcement and belief-based inputs.

B-tree search reinforcement learning for model based intelligent agent

NASA Astrophysics Data System (ADS)

Bhuvaneswari, S.; Vignashwaran, R.

2013-03-01

Agents trained by learning techniques provide a powerful approximation of active solutions for naive approaches. In this study using B - Trees implying reinforced learning the data search for information retrieval is moderated to achieve accuracy with minimum search time. The impact of variables and tactics applied in training are determined using reinforcement learning. Agents based on these techniques perform satisfactory baseline and act as finite agents based on the predetermined model against competitors from the course.

Vector-based navigation using grid-like representations in artificial agents.

PubMed

Banino, Andrea; Barry, Caswell; Uria, Benigno; Blundell, Charles; Lillicrap, Timothy; Mirowski, Piotr; Pritzel, Alexander; Chadwick, Martin J; Degris, Thomas; Modayil, Joseph; Wayne, Greg; Soyer, Hubert; Viola, Fabio; Zhang, Brian; Goroshin, Ross; Rabinowitz, Neil; Pascanu, Razvan; Beattie, Charlie; Petersen, Stig; Sadik, Amir; Gaffney, Stephen; King, Helen; Kavukcuoglu, Koray; Hassabis, Demis; Hadsell, Raia; Kumaran, Dharshan

2018-05-01

Deep neural networks have achieved impressive successes in fields ranging from object recognition to complex games such as Go 1,2 . Navigation, however, remains a substantial challenge for artificial agents, with deep neural networks trained by reinforcement learning 3-5 failing to rival the proficiency of mammalian spatial behaviour, which is underpinned by grid cells in the entorhinal cortex 6 . Grid cells are thought to provide a multi-scale periodic representation that functions as a metric for coding space 7,8 and is critical for integrating self-motion (path integration) 6,7,9 and planning direct trajectories to goals (vector-based navigation) 7,10,11 . Here we set out to leverage the computational functions of grid cells to develop a deep reinforcement learning agent with mammal-like navigational abilities. We first trained a recurrent network to perform path integration, leading to the emergence of representations resembling grid cells, as well as other entorhinal cell types 12 . We then showed that this representation provided an effective basis for an agent to locate goals in challenging, unfamiliar, and changeable environments-optimizing the primary objective of navigation through deep reinforcement learning. The performance of agents endowed with grid-like representations surpassed that of an expert human and comparison agents, with the metric quantities necessary for vector-based navigation derived from grid-like units within the network. Furthermore, grid-like representations enabled agents to conduct shortcut behaviours reminiscent of those performed by mammals. Our findings show that emergent grid-like representations furnish agents with a Euclidean spatial metric and associated vector operations, providing a foundation for proficient navigation. As such, our results support neuroscientific theories that see grid cells as critical for vector-based navigation 7,10,11 , demonstrating that the latter can be combined with path-based strategies to support navigation in challenging environments.

Effect of reinforcement learning on coordination of multiangent systems

NASA Astrophysics Data System (ADS)

Bukkapatnam, Satish T. S.; Gao, Greg

2000-12-01

For effective coordination of distributed environments involving multiagent systems, learning ability of each agent in the environment plays a crucial role. In this paper, we develop a simple group learning method based on reinforcement, and study its effect on coordination through application to a supply chain procurement scenario involving a computer manufacturer. Here, all parties are represented by self-interested, autonomous agents, each capable of performing specific simple tasks. They negotiate with each other to perform complex tasks and thus coordinate supply chain procurement. Reinforcement learning is intended to enable each agent to reach a best negotiable price within a shortest possible time. Our simulations of the application scenario under different learning strategies reveals the positive effects of reinforcement learning on an agent's as well as the system's performance.

Homeostatic Agent for General Environment

NASA Astrophysics Data System (ADS)

Yoshida, Naoto

2018-03-01

One of the essential aspect in biological agents is dynamic stability. This aspect, called homeostasis, is widely discussed in ethology, neuroscience and during the early stages of artificial intelligence. Ashby's homeostats are general-purpose learning machines for stabilizing essential variables of the agent in the face of general environments. However, despite their generality, the original homeostats couldn't be scaled because they searched their parameters randomly. In this paper, first we re-define the objective of homeostats as the maximization of a multi-step survival probability from the view point of sequential decision theory and probabilistic theory. Then we show that this optimization problem can be treated by using reinforcement learning algorithms with special agent architectures and theoretically-derived intrinsic reward functions. Finally we empirically demonstrate that agents with our architecture automatically learn to survive in a given environment, including environments with visual stimuli. Our survival agents can learn to eat food, avoid poison and stabilize essential variables through theoretically-derived single intrinsic reward formulations.

Human-level control through deep reinforcement learning.

PubMed

Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David; Rusu, Andrei A; Veness, Joel; Bellemare, Marc G; Graves, Alex; Riedmiller, Martin; Fidjeland, Andreas K; Ostrovski, Georg; Petersen, Stig; Beattie, Charles; Sadik, Amir; Antonoglou, Ioannis; King, Helen; Kumaran, Dharshan; Wierstra, Daan; Legg, Shane; Hassabis, Demis

2015-02-26

The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

Human-level control through deep reinforcement learning

NASA Astrophysics Data System (ADS)

Mnih, Volodymyr; Kavukcuoglu, Koray; Silver, David; Rusu, Andrei A.; Veness, Joel; Bellemare, Marc G.; Graves, Alex; Riedmiller, Martin; Fidjeland, Andreas K.; Ostrovski, Georg; Petersen, Stig; Beattie, Charles; Sadik, Amir; Antonoglou, Ioannis; King, Helen; Kumaran, Dharshan; Wierstra, Daan; Legg, Shane; Hassabis, Demis

2015-02-01

The theory of reinforcement learning provides a normative account, deeply rooted in psychological and neuroscientific perspectives on animal behaviour, of how agents may optimize their control of an environment. To use reinforcement learning successfully in situations approaching real-world complexity, however, agents are confronted with a difficult task: they must derive efficient representations of the environment from high-dimensional sensory inputs, and use these to generalize past experience to new situations. Remarkably, humans and other animals seem to solve this problem through a harmonious combination of reinforcement learning and hierarchical sensory processing systems, the former evidenced by a wealth of neural data revealing notable parallels between the phasic signals emitted by dopaminergic neurons and temporal difference reinforcement learning algorithms. While reinforcement learning agents have achieved some successes in a variety of domains, their applicability has previously been limited to domains in which useful features can be handcrafted, or to domains with fully observed, low-dimensional state spaces. Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. We tested this agent on the challenging domain of classic Atari 2600 games. We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters. This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.

Place preference and vocal learning rely on distinct reinforcers in songbirds.

PubMed

Murdoch, Don; Chen, Ruidong; Goldberg, Jesse H

2018-04-30

In reinforcement learning (RL) agents are typically tasked with maximizing a single objective function such as reward. But it remains poorly understood how agents might pursue distinct objectives at once. In machines, multiobjective RL can be achieved by dividing a single agent into multiple sub-agents, each of which is shaped by agent-specific reinforcement, but it remains unknown if animals adopt this strategy. Here we use songbirds to test if navigation and singing, two behaviors with distinct objectives, can be differentially reinforced. We demonstrate that strobe flashes aversively condition place preference but not song syllables. Brief noise bursts aversively condition song syllables but positively reinforce place preference. Thus distinct behavior-generating systems, or agencies, within a single animal can be shaped by correspondingly distinct reinforcement signals. Our findings suggest that spatially segregated vocal circuits can solve a credit assignment problem associated with multiobjective learning.

Deep Reinforcement Learning of Cell Movement in the Early Stage of C. elegans Embryogenesis.

PubMed

Wang, Zi; Wang, Dali; Li, Chengcheng; Xu, Yichi; Li, Husheng; Bao, Zhirong

2018-04-25

Cell movement in the early phase of C. elegans development is regulated by a highly complex process in which a set of rules and connections are formulated at distinct scales. Previous efforts have demonstrated that agent-based, multi-scale modeling systems can integrate physical and biological rules and provide new avenues to study developmental systems. However, the application of these systems to model cell movement is still challenging and requires a comprehensive understanding of regulatory networks at the right scales. Recent developments in deep learning and reinforcement learning provide an unprecedented opportunity to explore cell movement using 3D time-lapse microscopy images. We present a deep reinforcement learning approach within an agent-based modeling system to characterize cell movement in the embryonic development of C. elegans. Our modeling system captures the complexity of cell movement patterns in the embryo and overcomes the local optimization problem encountered by traditional rule-based, agent-based modeling that uses greedy algorithms. We tested our model with two real developmental processes: the anterior movement of the Cpaaa cell via intercalation and the rearrangement of the superficial left-right asymmetry. In the first case, the model results suggested that Cpaaa's intercalation is an active directional cell movement caused by the continuous effects from a longer distance (farther than the length of two adjacent cells), as opposed to a passive movement caused by neighbor cell movements. In the second case, a leader-follower mechanism well explained the collective cell movement pattern in the asymmetry rearrangement. These results showed that our approach to introduce deep reinforcement learning into agent-based modeling can test regulatory mechanisms by exploring cell migration paths in a reverse engineering perspective. This model opens new doors to explore the large datasets generated by live imaging. Source code is available at https://github.com/zwang84/drl4cellmovement. dwang7@utk.edu, baoz@mskcc.org. Supplementary data are available at Bioinformatics online.

Dissociable neural representations of reinforcement and belief prediction errors underlie strategic learning

PubMed Central

Zhu, Lusha; Mathewson, Kyle E.; Hsu, Ming

2012-01-01

Decision-making in the presence of other competitive intelligent agents is fundamental for social and economic behavior. Such decisions require agents to behave strategically, where in addition to learning about the rewards and punishments available in the environment, they also need to anticipate and respond to actions of others competing for the same rewards. However, whereas we know much about strategic learning at both theoretical and behavioral levels, we know relatively little about the underlying neural mechanisms. Here, we show using a multi-strategy competitive learning paradigm that strategic choices can be characterized by extending the reinforcement learning (RL) framework to incorporate agents’ beliefs about the actions of their opponents. Furthermore, using this characterization to generate putative internal values, we used model-based functional magnetic resonance imaging to investigate neural computations underlying strategic learning. We found that the distinct notions of prediction errors derived from our computational model are processed in a partially overlapping but distinct set of brain regions. Specifically, we found that the RL prediction error was correlated with activity in the ventral striatum. In contrast, activity in the ventral striatum, as well as the rostral anterior cingulate (rACC), was correlated with a previously uncharacterized belief-based prediction error. Furthermore, activity in rACC reflected individual differences in degree of engagement in belief learning. These results suggest a model of strategic behavior where learning arises from interaction of dissociable reinforcement and belief-based inputs. PMID:22307594

Dynamic route and departure time choice model based on self-adaptive reference point and reinforcement learning

NASA Astrophysics Data System (ADS)

Li, Xue-yan; Li, Xue-mei; Yang, Lingrun; Li, Jing

2018-07-01

Most of the previous studies on dynamic traffic assignment are based on traditional analytical framework, for instance, the idea of Dynamic User Equilibrium has been widely used in depicting both the route choice and the departure time choice. However, some recent studies have demonstrated that the dynamic traffic flow assignment largely depends on travelers' rationality degree, travelers' heterogeneity and what the traffic information the travelers have. In this paper, we develop a new self-adaptive multi agent model to depict travelers' behavior in Dynamic Traffic Assignment. We use Cumulative Prospect Theory with heterogeneous reference points to illustrate travelers' bounded rationality. We use reinforcement-learning model to depict travelers' route and departure time choosing behavior under the condition of imperfect information. We design the evolution rule of travelers' expected arrival time and the algorithm of traffic flow assignment. Compared with the traditional model, the self-adaptive multi agent model we proposed in this paper can effectively help travelers avoid the rush hour. Finally, we report and analyze the effect of travelers' group behavior on the transportation system, and give some insights into the relation between travelers' group behavior and the performance of transportation system.

Analysis of the Pricing Process in Electricity Market using Multi-Agent Model

NASA Astrophysics Data System (ADS)

Shimomura, Takahiro; Saisho, Yuichi; Fujii, Yasumasa; Yamaji, Kenji

Many electric utilities world-wide have been forced to change their ways of doing business, from vertically integrated mechanisms to open market systems. We are facing urgent issues about how we design the structures of power market systems. In order to settle down these issues, many studies have been made with market models of various characteristics and regulations. The goal of modeling analysis is to enrich our understanding of fundamental process that may appear. However, there are many kinds of modeling methods. Each has drawback and advantage about validity and versatility. This paper presents two kinds of methods to construct multi-agent market models. One is based on game theory and another is based on reinforcement learning. By comparing the results of the two methods, they can advance in validity and help us figure out potential problems in electricity markets which have oligopolistic generators, demand fluctuation and inelastic demand. Moreover, this model based on reinforcement learning enables us to consider characteristics peculiar to electricity markets which have plant unit characteristics, seasonable and hourly demand fluctuation, real-time regulation market and operating reserve market. This model figures out importance of the share of peak-load-plants and the way of designing operating reserve market.

Reinforcement learning agents providing advice in complex video games

NASA Astrophysics Data System (ADS)

Taylor, Matthew E.; Carboni, Nicholas; Fachantidis, Anestis; Vlahavas, Ioannis; Torrey, Lisa

2014-01-01

This article introduces a teacher-student framework for reinforcement learning, synthesising and extending material that appeared in conference proceedings [Torrey, L., & Taylor, M. E. (2013)]. Teaching on a budget: Agents advising agents in reinforcement learning. {Proceedings of the international conference on autonomous agents and multiagent systems}] and in a non-archival workshop paper [Carboni, N., &Taylor, M. E. (2013, May)]. Preliminary results for 1 vs. 1 tactics in StarCraft. {Proceedings of the adaptive and learning agents workshop (at AAMAS-13)}]. In this framework, a teacher agent instructs a student agent by suggesting actions the student should take as it learns. However, the teacher may only give such advice a limited number of times. We present several novel algorithms that teachers can use to budget their advice effectively, and we evaluate them in two complex video games: StarCraft and Pac-Man. Our results show that the same amount of advice, given at different moments, can have different effects on student learning, and that teachers can significantly affect student learning even when students use different learning methods and state representations.

An intelligent agent for optimal river-reservoir system management

NASA Astrophysics Data System (ADS)

Rieker, Jeffrey D.; Labadie, John W.

2012-09-01

A generalized software package is presented for developing an intelligent agent for stochastic optimization of complex river-reservoir system management and operations. Reinforcement learning is an approach to artificial intelligence for developing a decision-making agent that learns the best operational policies without the need for explicit probabilistic models of hydrologic system behavior. The agent learns these strategies experientially in a Markov decision process through observational interaction with the environment and simulation of the river-reservoir system using well-calibrated models. The graphical user interface for the reinforcement learning process controller includes numerous learning method options and dynamic displays for visualizing the adaptive behavior of the agent. As a case study, the generalized reinforcement learning software is applied to developing an intelligent agent for optimal management of water stored in the Truckee river-reservoir system of California and Nevada for the purpose of streamflow augmentation for water quality enhancement. The intelligent agent successfully learns long-term reservoir operational policies that specifically focus on mitigating water temperature extremes during persistent drought periods that jeopardize the survival of threatened and endangered fish species.

Adaptivity in Agent-Based Routing for Data Networks

NASA Technical Reports Server (NTRS)

Wolpert, David H.; Kirshner, Sergey; Merz, Chris J.; Turner, Kagan

2000-01-01

Adaptivity, both of the individual agents and of the interaction structure among the agents, seems indispensable for scaling up multi-agent systems (MAS s) in noisy environments. One important consideration in designing adaptive agents is choosing their action spaces to be as amenable as possible to machine learning techniques, especially to reinforcement learning (RL) techniques. One important way to have the interaction structure connecting agents itself be adaptive is to have the intentions and/or actions of the agents be in the input spaces of the other agents, much as in Stackelberg games. We consider both kinds of adaptivity in the design of a MAS to control network packet routing. We demonstrate on the OPNET event-driven network simulator the perhaps surprising fact that simply changing the action space of the agents to be better suited to RL can result in very large improvements in their potential performance: at their best settings, our learning-amenable router agents achieve throughputs up to three and one half times better than that of the standard Bellman-Ford routing algorithm, even when the Bellman-Ford protocol traffic is maintained. We then demonstrate that much of that potential improvement can be realized by having the agents learn their settings when the agent interaction structure is itself adaptive.

Evolution with Reinforcement Learning in Negotiation

PubMed Central

Zou, Yi; Zhan, Wenjie; Shao, Yuan

2014-01-01

Adaptive behavior depends less on the details of the negotiation process and makes more robust predictions in the long term as compared to in the short term. However, the extant literature on population dynamics for behavior adjustment has only examined the current situation. To offset this limitation, we propose a synergy of evolutionary algorithm and reinforcement learning to investigate long-term collective performance and strategy evolution. The model adopts reinforcement learning with a tradeoff between historical and current information to make decisions when the strategies of agents evolve through repeated interactions. The results demonstrate that the strategies in populations converge to stable states, and the agents gradually form steady negotiation habits. Agents that adopt reinforcement learning perform better in payoff, fairness, and stableness than their counterparts using classic evolutionary algorithm. PMID:25048108

Evolution with reinforcement learning in negotiation.

PubMed

Zou, Yi; Zhan, Wenjie; Shao, Yuan

2014-01-01

Adaptive behavior depends less on the details of the negotiation process and makes more robust predictions in the long term as compared to in the short term. However, the extant literature on population dynamics for behavior adjustment has only examined the current situation. To offset this limitation, we propose a synergy of evolutionary algorithm and reinforcement learning to investigate long-term collective performance and strategy evolution. The model adopts reinforcement learning with a tradeoff between historical and current information to make decisions when the strategies of agents evolve through repeated interactions. The results demonstrate that the strategies in populations converge to stable states, and the agents gradually form steady negotiation habits. Agents that adopt reinforcement learning perform better in payoff, fairness, and stableness than their counterparts using classic evolutionary algorithm.

A self-taught artificial agent for multi-physics computational model personalization.

PubMed

Neumann, Dominik; Mansi, Tommaso; Itu, Lucian; Georgescu, Bogdan; Kayvanpour, Elham; Sedaghat-Hamedani, Farbod; Amr, Ali; Haas, Jan; Katus, Hugo; Meder, Benjamin; Steidl, Stefan; Hornegger, Joachim; Comaniciu, Dorin

2016-12-01

Personalization is the process of fitting a model to patient data, a critical step towards application of multi-physics computational models in clinical practice. Designing robust personalization algorithms is often a tedious, time-consuming, model- and data-specific process. We propose to use artificial intelligence concepts to learn this task, inspired by how human experts manually perform it. The problem is reformulated in terms of reinforcement learning. In an off-line phase, Vito, our self-taught artificial agent, learns a representative decision process model through exploration of the computational model: it learns how the model behaves under change of parameters. The agent then automatically learns an optimal strategy for on-line personalization. The algorithm is model-independent; applying it to a new model requires only adjusting few hyper-parameters of the agent and defining the observations to match. The full knowledge of the model itself is not required. Vito was tested in a synthetic scenario, showing that it could learn how to optimize cost functions generically. Then Vito was applied to the inverse problem of cardiac electrophysiology and the personalization of a whole-body circulation model. The obtained results suggested that Vito could achieve equivalent, if not better goodness of fit than standard methods, while being more robust (up to 11% higher success rates) and with faster (up to seven times) convergence rate. Our artificial intelligence approach could thus make personalization algorithms generalizable and self-adaptable to any patient and any model. Copyright © 2016. Published by Elsevier B.V.

Collaborating Fuzzy Reinforcement Learning Agents

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1997-01-01

Earlier, we introduced GARIC-Q, a new method for doing incremental Dynamic Programming using a society of intelligent agents which are controlled at the top level by Fuzzy Relearning and at the local level, each agent learns and operates based on ANTARCTIC, a technique for fuzzy reinforcement learning. In this paper, we show that it is possible for these agents to compete in order to affect the selected control policy but at the same time, they can collaborate while investigating the state space. In this model, the evaluator or the critic learns by observing all the agents behaviors but the control policy changes only based on the behavior of the winning agent also known as the super agent.

Pragmatically Framed Cross-Situational Noun Learning Using Computational Reinforcement Models

PubMed Central

Najnin, Shamima; Banerjee, Bonny

2018-01-01

Cross-situational learning and social pragmatic theories are prominent mechanisms for learning word meanings (i.e., word-object pairs). In this paper, the role of reinforcement is investigated for early word-learning by an artificial agent. When exposed to a group of speakers, the agent comes to understand an initial set of vocabulary items belonging to the language used by the group. Both cross-situational learning and social pragmatic theory are taken into account. As social cues, joint attention and prosodic cues in caregiver's speech are considered. During agent-caregiver interaction, the agent selects a word from the caregiver's utterance and learns the relations between that word and the objects in its visual environment. The “novel words to novel objects” language-specific constraint is assumed for computing rewards. The models are learned by maximizing the expected reward using reinforcement learning algorithms [i.e., table-based algorithms: Q-learning, SARSA, SARSA-λ, and neural network-based algorithms: Q-learning for neural network (Q-NN), neural-fitted Q-network (NFQ), and deep Q-network (DQN)]. Neural network-based reinforcement learning models are chosen over table-based models for better generalization and quicker convergence. Simulations are carried out using mother-infant interaction CHILDES dataset for learning word-object pairings. Reinforcement is modeled in two cross-situational learning cases: (1) with joint attention (Attentional models), and (2) with joint attention and prosodic cues (Attentional-prosodic models). Attentional-prosodic models manifest superior performance to Attentional ones for the task of word-learning. The Attentional-prosodic DQN outperforms existing word-learning models for the same task. PMID:29441027

Reinforcement Learning Multi-Agent Modeling of Decision-Making Agents for the Study of Transboundary Surface Water Conflicts with Application to the Syr Darya River Basin

NASA Astrophysics Data System (ADS)

Riegels, N.; Siegfried, T.; Pereira Cardenal, S. J.; Jensen, R. A.; Bauer-Gottwein, P.

2008-12-01

In most economics--driven approaches to optimizing water use at the river basin scale, the system is modelled deterministically with the goal of maximizing overall benefits. However, actual operation and allocation decisions must be made under hydrologic and economic uncertainty. In addition, river basins often cross political boundaries, and different states may not be motivated to cooperate so as to maximize basin- scale benefits. Even within states, competing agents such as irrigation districts, municipal water agencies, and large industrial users may not have incentives to cooperate to realize efficiency gains identified in basin- level studies. More traditional simulation--optimization approaches assume pre-commitment by individual agents and stakeholders and unconditional compliance on each side. While this can help determine attainable gains and tradeoffs from efficient management, such hardwired policies do not account for dynamic feedback between agents themselves or between agents and their environments (e.g. due to climate change etc.). In reality however, we are dealing with an out-of-equilibrium multi-agent system, where there is neither global knowledge nor global control, but rather continuous strategic interaction between decision making agents. Based on the theory of stochastic games, we present a computational framework that allows for studying the dynamic feedback between decision--making agents themselves and an inherently uncertain environment in a spatially and temporally distributed manner. Agents with decision-making control over water allocation such as countries, irrigation districts, and municipalities are represented by reinforcement learning agents and coupled to a detailed hydrologic--economic model. This approach emphasizes learning by agents from their continuous interaction with other agents and the environment. It provides a convenient framework for the solution of the problem of dynamic decision-making in a mixed cooperative / non-cooperative environment with which different institutional setups and incentive systems can be studied so to identify reasonable ways to reach desirable, Pareto--optimal allocation outcomes. Preliminary results from an application to the Syr Darya river basin in Central Asia will be presented and discussed. The Syr Darya River is a classic example of a transboundary river basin in which basin-wide efficiency gains identified in optimization studies have not been sufficient to induce cooperative management of the river by the riparian states.

Emotional Multiagent Reinforcement Learning in Spatial Social Dilemmas.

PubMed

Yu, Chao; Zhang, Minjie; Ren, Fenghui; Tan, Guozhen

2015-12-01

Social dilemmas have attracted extensive interest in the research of multiagent systems in order to study the emergence of cooperative behaviors among selfish agents. Understanding how agents can achieve cooperation in social dilemmas through learning from local experience is a critical problem that has motivated researchers for decades. This paper investigates the possibility of exploiting emotions in agent learning in order to facilitate the emergence of cooperation in social dilemmas. In particular, the spatial version of social dilemmas is considered to study the impact of local interactions on the emergence of cooperation in the whole system. A double-layered emotional multiagent reinforcement learning framework is proposed to endow agents with internal cognitive and emotional capabilities that can drive these agents to learn cooperative behaviors. Experimental results reveal that various network topologies and agent heterogeneities have significant impacts on agent learning behaviors in the proposed framework, and under certain circumstances, high levels of cooperation can be achieved among the agents.

Preliminary Work for Examining the Scalability of Reinforcement Learning

NASA Technical Reports Server (NTRS)

Clouse, Jeff

1998-01-01

Researchers began studying automated agents that learn to perform multiple-step tasks early in the history of artificial intelligence (Samuel, 1963; Samuel, 1967; Waterman, 1970; Fikes, Hart & Nilsonn, 1972). Multiple-step tasks are tasks that can only be solved via a sequence of decisions, such as control problems, robotics problems, classic problem-solving, and game-playing. The objective of agents attempting to learn such tasks is to use the resources they have available in order to become more proficient at the tasks. In particular, each agent attempts to develop a good policy, a mapping from states to actions, that allows it to select actions that optimize a measure of its performance on the task; for example, reducing the number of steps necessary to complete the task successfully. Our study focuses on reinforcement learning, a set of learning techniques where the learner performs trial-and-error experiments in the task and adapts its policy based on the outcome of those experiments. Much of the work in reinforcement learning has focused on a particular, simple representation, where every problem state is represented explicitly in a table, and associated with each state are the actions that can be chosen in that state. A major advantage of this table lookup representation is that one can prove that certain reinforcement learning techniques will develop an optimal policy for the current task. The drawback is that the representation limits the application of reinforcement learning to multiple-step tasks with relatively small state-spaces. There has been a little theoretical work that proves that convergence to optimal solutions can be obtained when using generalization structures, but the structures are quite simple. The theory says little about complex structures, such as multi-layer, feedforward artificial neural networks (Rumelhart & McClelland, 1986), but empirical results indicate that the use of reinforcement learning with such structures is promising. These empirical results make no theoretical claims, nor compare the policies produced to optimal policies. A goal of our work is to be able to make the comparison between an optimal policy and one stored in an artificial neural network. A difficulty of performing such a study is finding a multiple-step task that is small enough that one can find an optimal policy using table lookup, yet large enough that, for practical purposes, an artificial neural network is really required. We have identified a limited form of the game OTHELLO as satisfying these requirements. The work we report here is in the very preliminary stages of research, but this paper provides background for the problem being studied and a description of our initial approach to examining the problem. In the remainder of this paper, we first describe reinforcement learning in more detail. Next, we present the game OTHELLO. Finally we argue that a restricted form of the game meets the requirements of our study, and describe our preliminary approach to finding an optimal solution to the problem.

Attention control learning in the decision space using state estimation

NASA Astrophysics Data System (ADS)

Gharaee, Zahra; Fatehi, Alireza; Mirian, Maryam S.; Nili Ahmadabadi, Majid

2016-05-01

The main goal of this paper is modelling attention while using it in efficient path planning of mobile robots. The key challenge in concurrently aiming these two goals is how to make an optimal, or near-optimal, decision in spite of time and processing power limitations, which inherently exist in a typical multi-sensor real-world robotic application. To efficiently recognise the environment under these two limitations, attention of an intelligent agent is controlled by employing the reinforcement learning framework. We propose an estimation method using estimated mixture-of-experts task and attention learning in perceptual space. An agent learns how to employ its sensory resources, and when to stop observing, by estimating its perceptual space. In this paper, static estimation of the state space in a learning task problem, which is examined in the WebotsTM simulator, is performed. Simulation results show that a robot learns how to achieve an optimal policy with a controlled cost by estimating the state space instead of continually updating sensory information.

Learning to cooperate in solving the traveling salesman problem.

PubMed

Qi, Dehu; Sun, Ron

2005-01-01

A cooperative team of agents may perform many tasks better than single agents. The question is how cooperation among self-interested agents should be achieved. It is important that, while we encourage cooperation among agents in a team, we maintain autonomy of individual agents as much as possible, so as to maintain flexibility and generality. This paper presents an approach based on bidding utilizing reinforcement values acquired through reinforcement learning. We tested and analyzed this approach and demonstrated that a team indeed performed better than the best single agent as well as the average of single agents.

Fuzzy Q-Learning for Generalization of Reinforcement Learning

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1996-01-01

Fuzzy Q-Learning, introduced earlier by the author, is an extension of Q-Learning into fuzzy environments. GARIC is a methodology for fuzzy reinforcement learning. In this paper, we introduce GARIC-Q, a new method for doing incremental Dynamic Programming using a society of intelligent agents which are controlled at the top level by Fuzzy Q-Learning and at the local level, each agent learns and operates based on GARIC. GARIC-Q improves the speed and applicability of Fuzzy Q-Learning through generalization of input space by using fuzzy rules and bridges the gap between Q-Learning and rule based intelligent systems.

Analysis of Foreign Exchange Interventions by Intervention Agent with an Artificial Market Approach

NASA Astrophysics Data System (ADS)

Matsui, Hiroki; Tojo, Satoshi

We propose a multi-agent system which learns intervention policies and evaluates the effect of interventions in an artificial foreign exchange market. Izumi et al. had presented a system called AGEDASI TOF to simulate artificial market, together with a support system for the government to decide foreign exchange policies. However, the system needed to fix the amount of governmental intervention prior to the simulation, and was not realistic. In addition, the interventions in the system did not affect supply and demand of currencies; thus we could not discuss the effect of intervention correctly. First, we improve the system so as to make much of the weights of influential factors. Thereafter, we introduce an intervention agent that has the role of the central bank to stabilize the market. We could show that the agent learned the effective intervention policies through the reinforcement learning, and that the exchange rate converged to a certain extent in the expected range. We could also estimate the amount of intervention, showing the efficacy of signaling. In this model, in order to investigate the aliasing of the perception of the intervention agent, we introduced a pseudo-agent who was supposed to be able to observe all the behaviors of dealer agents; with this super-agent, we discussed the adequate granularity for a market state description.

Agent-based traffic management and reinforcement learning in congested intersection network.

DOT National Transportation Integrated Search

2012-08-01

This study evaluates the performance of traffic control systems based on reinforcement learning (RL), also called approximate dynamic programming (ADP). Two algorithms have been selected for testing: 1) Q-learning and 2) approximate dynamic programmi...

Stochastic Reinforcement Benefits Skill Acquisition

ERIC Educational Resources Information Center

Dayan, Eran; Averbeck, Bruno B.; Richmond, Barry J.; Cohen, Leonardo G.

2014-01-01

Learning complex skills is driven by reinforcement, which facilitates both online within-session gains and retention of the acquired skills. Yet, in ecologically relevant situations, skills are often acquired when mapping between actions and rewarding outcomes is unknown to the learning agent, resulting in reinforcement schedules of a stochastic…

Multi-Agent Methods for the Configuration of Random Nanocomputers

NASA Technical Reports Server (NTRS)

Lawson, John W.

2004-01-01

As computational devices continue to shrink, the cost of manufacturing such devices is expected to grow exponentially. One alternative to the costly, detailed design and assembly of conventional computers is to place the nano-electronic components randomly on a chip. The price for such a trivial assembly process is that the resulting chip would not be programmable by conventional means. In this work, we show that such random nanocomputers can be adaptively programmed using multi-agent methods. This is accomplished through the optimization of an associated high dimensional error function. By representing each of the independent variables as a reinforcement learning agent, we are able to achieve convergence must faster than with other methods, including simulated annealing. Standard combinational logic circuits such as adders and multipliers are implemented in a straightforward manner. In addition, we show that the intrinsic flexibility of these adaptive methods allows the random computers to be reconfigured easily, making them reusable. Recovery from faults is also demonstrated.

Optimal Wonderful Life Utility Functions in Multi-Agent Systems

NASA Technical Reports Server (NTRS)

Wolpert, David H.; Tumer, Kagan; Swanson, Keith (Technical Monitor)

2000-01-01

The mathematics of Collective Intelligence (COINs) is concerned with the design of multi-agent systems so as to optimize an overall global utility function when those systems lack centralized communication and control. Typically in COINs each agent runs a distinct Reinforcement Learning (RL) algorithm, so that much of the design problem reduces to how best to initialize/update each agent's private utility function, as far as the ensuing value of the global utility is concerned. Traditional team game solutions to this problem assign to each agent the global utility as its private utility function. In previous work we used the COIN framework to derive the alternative Wonderful Life Utility (WLU), and experimentally established that having the agents use it induces global utility performance up to orders of magnitude superior to that induced by use of the team game utility. The WLU has a free parameter (the clamping parameter) which we simply set to zero in that previous work. Here we derive the optimal value of the clamping parameter, and demonstrate experimentally that using that optimal value can result in significantly improved performance over that of clamping to zero, over and above the improvement beyond traditional approaches.

Product Distribution Theory for Control of Multi-Agent Systems

NASA Technical Reports Server (NTRS)

Lee, Chia Fan; Wolpert, David H.

2004-01-01

Product Distribution (PD) theory is a new framework for controlling Multi-Agent Systems (MAS's). First we review one motivation of PD theory, as the information-theoretic extension of conventional full-rationality game theory to the case of bounded rational agents. In this extension the equilibrium of the game is the optimizer of a Lagrangian of the (probability distribution of) the joint stare of the agents. Accordingly we can consider a team game in which the shared utility is a performance measure of the behavior of the MAS. For such a scenario the game is at equilibrium - the Lagrangian is optimized - when the joint distribution of the agents optimizes the system's expected performance. One common way to find that equilibrium is to have each agent run a reinforcement learning algorithm. Here we investigate the alternative of exploiting PD theory to run gradient descent on the Lagrangian. We present computer experiments validating some of the predictions of PD theory for how best to do that gradient descent. We also demonstrate how PD theory can improve performance even when we are not allowed to rerun the MAS from different initial conditions, a requirement implicit in some previous work.

Multiagent cooperation and competition with deep reinforcement learning.

PubMed

Tampuu, Ardi; Matiisen, Tambet; Kodelja, Dorian; Kuzovkin, Ilya; Korjus, Kristjan; Aru, Juhan; Aru, Jaan; Vicente, Raul

2017-01-01

Evolution of cooperation and competition can appear when multiple adaptive agents share a biological, social, or technological niche. In the present work we study how cooperation and competition emerge between autonomous agents that learn by reinforcement while using only their raw visual input as the state representation. In particular, we extend the Deep Q-Learning framework to multiagent environments to investigate the interaction between two learning agents in the well-known video game Pong. By manipulating the classical rewarding scheme of Pong we show how competitive and collaborative behaviors emerge. We also describe the progression from competitive to collaborative behavior when the incentive to cooperate is increased. Finally we show how learning by playing against another adaptive agent, instead of against a hard-wired algorithm, results in more robust strategies. The present work shows that Deep Q-Networks can become a useful tool for studying decentralized learning of multiagent systems coping with high-dimensional environments.

Multiagent cooperation and competition with deep reinforcement learning

PubMed Central

Kodelja, Dorian; Kuzovkin, Ilya; Korjus, Kristjan; Aru, Juhan; Aru, Jaan; Vicente, Raul

2017-01-01

Evolution of cooperation and competition can appear when multiple adaptive agents share a biological, social, or technological niche. In the present work we study how cooperation and competition emerge between autonomous agents that learn by reinforcement while using only their raw visual input as the state representation. In particular, we extend the Deep Q-Learning framework to multiagent environments to investigate the interaction between two learning agents in the well-known video game Pong. By manipulating the classical rewarding scheme of Pong we show how competitive and collaborative behaviors emerge. We also describe the progression from competitive to collaborative behavior when the incentive to cooperate is increased. Finally we show how learning by playing against another adaptive agent, instead of against a hard-wired algorithm, results in more robust strategies. The present work shows that Deep Q-Networks can become a useful tool for studying decentralized learning of multiagent systems coping with high-dimensional environments. PMID:28380078

Feature Reinforcement Learning: Part I. Unstructured MDPs

NASA Astrophysics Data System (ADS)

Hutter, Marcus

2009-12-01

General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small finite state Markov decision processes (MDPs). Up to now, extracting the right state representations out of bare observations, that is, reducing the general agent setup to the MDP framework, is an art that involves significant effort by designers. The primary goal of this work is to automate the reduction process and thereby significantly expand the scope of many existing reinforcement learning algorithms and the agents that employ them. Before we can think of mechanizing this search for suitable MDPs, we need a formal objective criterion. The main contribution of this article is to develop such a criterion. I also integrate the various parts into one learning algorithm. Extensions to more realistic dynamic Bayesian networks are developed in Part II (Hutter, 2009c). The role of POMDPs is also considered there.

Collective Machine Learning: Team Learning and Classification in Multi-Agent Systems

ERIC Educational Resources Information Center

Gifford, Christopher M.

2009-01-01

This dissertation focuses on the collaboration of multiple heterogeneous, intelligent agents (hardware or software) which collaborate to learn a task and are capable of sharing knowledge. The concept of collaborative learning in multi-agent and multi-robot systems is largely under studied, and represents an area where further research is needed to…

Multi-Agent Framework for Virtual Learning Spaces.

ERIC Educational Resources Information Center

Sheremetov, Leonid; Nunez, Gustavo

1999-01-01

Discussion of computer-supported collaborative learning, distributed artificial intelligence, and intelligent tutoring systems focuses on the concept of agents, and describes a virtual learning environment that has a multi-agent system. Describes a model of interactions in collaborative learning and discusses agents for Web-based virtual…

Learning to Predict Consequences as a Method of Knowledge Transfer in Reinforcement Learning.

PubMed

Chalmers, Eric; Contreras, Edgar Bermudez; Robertson, Brandon; Luczak, Artur; Gruber, Aaron

2017-04-17

The reinforcement learning (RL) paradigm allows agents to solve tasks through trial-and-error learning. To be capable of efficient, long-term learning, RL agents should be able to apply knowledge gained in the past to new tasks they may encounter in the future. The ability to predict actions' consequences may facilitate such knowledge transfer. We consider here domains where an RL agent has access to two kinds of information: agent-centric information with constant semantics across tasks, and environment-centric information, which is necessary to solve the task, but with semantics that differ between tasks. For example, in robot navigation, environment-centric information may include the robot's geographic location, while agent-centric information may include sensor readings of various nearby obstacles. We propose that these situations provide an opportunity for a very natural style of knowledge transfer, in which the agent learns to predict actions' environmental consequences using agent-centric information. These predictions contain important information about the affordances and dangers present in a novel environment, and can effectively transfer knowledge from agent-centric to environment-centric learning systems. Using several example problems including spatial navigation and network routing, we show that our knowledge transfer approach can allow faster and lower cost learning than existing alternatives.

A parameter control method in reinforcement learning to rapidly follow unexpected environmental changes.

PubMed

Murakoshi, Kazushi; Mizuno, Junya

2004-11-01

In order to rapidly follow unexpected environmental changes, we propose a parameter control method in reinforcement learning that changes each of learning parameters in appropriate directions. We determine each appropriate direction on the basis of relationships between behaviors and neuromodulators by considering an emergency as a key word. Computer experiments show that the agents using our proposed method could rapidly respond to unexpected environmental changes, not depending on either two reinforcement learning algorithms (Q-learning and actor-critic (AC) architecture) or two learning problems (discontinuous and continuous state-action problems).

Machine Learning Control For Highly Reconfigurable High-Order Systems

DTIC Science & Technology

2015-01-02

develop and flight test a Reinforcement Learning based approach for autonomous tracking of ground targets using a fixed wing Unmanned...Reinforcement Learning - based algorithms are developed for learning agents’ time dependent dynamics while also learning to control them. Three algorithms...to a wide range of engineering- based problems . Implementation of these solutions, however, is often complicated by the hysteretic, non-linear,

Learning to use working memory: a reinforcement learning gating model of rule acquisition in rats

PubMed Central

Lloyd, Kevin; Becker, Nadine; Jones, Matthew W.; Bogacz, Rafal

2012-01-01

Learning to form appropriate, task-relevant working memory representations is a complex process central to cognition. Gating models frame working memory as a collection of past observations and use reinforcement learning (RL) to solve the problem of when to update these observations. Investigation of how gating models relate to brain and behavior remains, however, at an early stage. The current study sought to explore the ability of simple RL gating models to replicate rule learning behavior in rats. Rats were trained in a maze-based spatial learning task that required animals to make trial-by-trial choices contingent upon their previous experience. Using an abstract version of this task, we tested the ability of two gating algorithms, one based on the Actor-Critic and the other on the State-Action-Reward-State-Action (SARSA) algorithm, to generate behavior consistent with the rats'. Both models produced rule-acquisition behavior consistent with the experimental data, though only the SARSA gating model mirrored faster learning following rule reversal. We also found that both gating models learned multiple strategies in solving the initial task, a property which highlights the multi-agent nature of such models and which is of importance in considering the neural basis of individual differences in behavior. PMID:23115551

What Can Reinforcement Learning Teach Us About Non-Equilibrium Quantum Dynamics

NASA Astrophysics Data System (ADS)

Bukov, Marin; Day, Alexandre; Sels, Dries; Weinberg, Phillip; Polkovnikov, Anatoli; Mehta, Pankaj

Equilibrium thermodynamics and statistical physics are the building blocks of modern science and technology. Yet, our understanding of thermodynamic processes away from equilibrium is largely missing. In this talk, I will reveal the potential of what artificial intelligence can teach us about the complex behaviour of non-equilibrium systems. Specifically, I will discuss the problem of finding optimal drive protocols to prepare a desired target state in quantum mechanical systems by applying ideas from Reinforcement Learning [one can think of Reinforcement Learning as the study of how an agent (e.g. a robot) can learn and perfect a given policy through interactions with an environment.]. The driving protocols learnt by our agent suggest that the non-equilibrium world features possibilities easily defying intuition based on equilibrium physics.

Towards a genetics-based adaptive agent to support flight testing

NASA Astrophysics Data System (ADS)

Cribbs, Henry Brown, III

Although the benefits of aircraft simulation have been known since the late 1960s, simulation almost always entails interaction with a human test pilot. This "pilot-in-the-loop" simulation process provides useful evaluative information to the aircraft designer and provides a training tool to the pilot. Emulation of a pilot during the early phases of the aircraft design process might provide designers a useful evaluative tool. Machine learning might emulate a pilot in a simulated aircraft/cockpit setting. Preliminary work in the application of machine learning techniques, such as reinforcement learning, to aircraft maneuvering have shown promise. These studies used simplified interfaces between machine learning agent and the aircraft simulation. The simulations employed low order equivalent system models. High-fidelity aircraft simulations exist, such as the simulations developed by NASA at its Dryden Flight Research Center. To expand the applicational domain of reinforcement learning to aircraft designs, this study presents a series of experiments that examine a reinforcement learning agent in the role of test pilot. The NASA X-31 and F-106 high-fidelity simulations provide realistic aircraft for the agent to maneuver. The approach of the study is to examine an agent possessing a genetic-based, artificial neural network to approximate long-term, expected cost (Bellman value) in a basic maneuvering task. The experiments evaluate different learning methods based on a common feedback function and an identical task. The learning methods evaluated are: Q-learning, Q(lambda)-learning, SARSA learning, and SARSA(lambda) learning. Experimental results indicate that, while prediction error remain quite high, similar, repeatable behaviors occur in both aircraft. Similar behavior exhibits portability of the agent between aircraft with different handling qualities (dynamics). Besides the adaptive behavior aspects of the study, the genetic algorithm used in the agent is shown to play an additive role in the shaping of the artificial neural network to the prediction task.

Reinforcement learning or active inference?

PubMed

Friston, Karl J; Daunizeau, Jean; Kiebel, Stefan J

2009-07-29

This paper questions the need for reinforcement learning or control theory when optimising behaviour. We show that it is fairly simple to teach an agent complicated and adaptive behaviours using a free-energy formulation of perception. In this formulation, agents adjust their internal states and sampling of the environment to minimize their free-energy. Such agents learn causal structure in the environment and sample it in an adaptive and self-supervised fashion. This results in behavioural policies that reproduce those optimised by reinforcement learning and dynamic programming. Critically, we do not need to invoke the notion of reward, value or utility. We illustrate these points by solving a benchmark problem in dynamic programming; namely the mountain-car problem, using active perception or inference under the free-energy principle. The ensuing proof-of-concept may be important because the free-energy formulation furnishes a unified account of both action and perception and may speak to a reappraisal of the role of dopamine in the brain.

Incorporation of perception-based information in robot learning using fuzzy reinforcement learning agents

NASA Astrophysics Data System (ADS)

Zhou, Changjiu; Meng, Qingchun; Guo, Zhongwen; Qu, Wiefen; Yin, Bo

2002-04-01

Robot learning in unstructured environments has been proved to be an extremely challenging problem, mainly because of many uncertainties always present in the real world. Human beings, on the other hand, seem to cope very well with uncertain and unpredictable environments, often relying on perception-based information. Furthermore, humans beings can also utilize perceptions to guide their learning on those parts of the perception-action space that are actually relevant to the task. Therefore, we conduct a research aimed at improving robot learning through the incorporation of both perception-based and measurement-based information. For this reason, a fuzzy reinforcement learning (FRL) agent is proposed in this paper. Based on a neural-fuzzy architecture, different kinds of information can be incorporated into the FRL agent to initialise its action network, critic network and evaluation feedback module so as to accelerate its learning. By making use of the global optimisation capability of GAs (genetic algorithms), a GA-based FRL (GAFRL) agent is presented to solve the local minima problem in traditional actor-critic reinforcement learning. On the other hand, with the prediction capability of the critic network, GAs can perform a more effective global search. Different GAFRL agents are constructed and verified by using the simulation model of a physical biped robot. The simulation analysis shows that the biped learning rate for dynamic balance can be improved by incorporating perception-based information on biped balancing and walking evaluation. The biped robot can find its application in ocean exploration, detection or sea rescue activity, as well as military maritime activity.

Self-healing in single and multiple fiber(s) reinforced polymer composites

NASA Astrophysics Data System (ADS)

Woldesenbet, E.

2010-06-01

You Polymer composites have been attractive medium to introduce the autonomic healing concept into modern day engineering materials. To date, there has been significant research in self-healing polymeric materials including several studies specifically in fiber reinforced polymers. Even though several methods have been suggested in autonomic healing materials, the concept of repair by bleeding of enclosed functional agents has garnered wide attention by the scientific community. A self-healing fiber reinforced polymer composite has been developed. Tensile tests are carried out on specimens that are fabricated by using the following components: hollow and solid glass fibers, healing agent, catalysts, multi-walled carbon nanotubes, and a polymer resin matrix. The test results have demonstrated that single fiber polymer composites and multiple fiber reinforced polymer matrix composites with healing agents and catalysts have provided 90.7% and 76.55% restoration of the original tensile strength, respectively. Incorporation of functionalized multi-walled carbon nanotubes in the healing medium of the single fiber polymer composite has provided additional efficiency. Healing is found to be localized, allowing multiple healing in the presence of several cracks.

Multi-agents and learning: Implications for Webusage mining.

PubMed

Lotfy, Hewayda M S; Khamis, Soheir M S; Aboghazalah, Maie M

2016-03-01

Characterization of user activities is an important issue in the design and maintenance of websites. Server weblog files have abundant information about the user's current interests. This information can be mined and analyzed therefore the administrators may be able to guide the users in their browsing activity so they may obtain relevant information in a shorter span of time to obtain user satisfaction. Web-based technology facilitates the creation of personally meaningful and socially useful knowledge through supportive interactions, communication and collaboration among educators, learners and information. This paper suggests a new methodology based on learning techniques for a Web-based Multiagent-based application to discover the hidden patterns in the user's visited links. It presents a new approach that involves unsupervised, reinforcement learning, and cooperation between agents. It is utilized to discover patterns that represent the user's profiles in a sample website into specific categories of materials using significance percentages. These profiles are used to make recommendations of interesting links and categories to the user. The experimental results of the approach showed successful user pattern recognition, and cooperative learning among agents to obtain user profiles. It indicates that combining different learning algorithms is capable of improving user satisfaction indicated by the percentage of precision, recall, the progressive category weight and F 1-measure.

Multi-agents and learning: Implications for Webusage mining

PubMed Central

Lotfy, Hewayda M.S.; Khamis, Soheir M.S.; Aboghazalah, Maie M.

2015-01-01

Characterization of user activities is an important issue in the design and maintenance of websites. Server weblog files have abundant information about the user’s current interests. This information can be mined and analyzed therefore the administrators may be able to guide the users in their browsing activity so they may obtain relevant information in a shorter span of time to obtain user satisfaction. Web-based technology facilitates the creation of personally meaningful and socially useful knowledge through supportive interactions, communication and collaboration among educators, learners and information. This paper suggests a new methodology based on learning techniques for a Web-based Multiagent-based application to discover the hidden patterns in the user’s visited links. It presents a new approach that involves unsupervised, reinforcement learning, and cooperation between agents. It is utilized to discover patterns that represent the user’s profiles in a sample website into specific categories of materials using significance percentages. These profiles are used to make recommendations of interesting links and categories to the user. The experimental results of the approach showed successful user pattern recognition, and cooperative learning among agents to obtain user profiles. It indicates that combining different learning algorithms is capable of improving user satisfaction indicated by the percentage of precision, recall, the progressive category weight and F1-measure. PMID:26966569

Needs, Pains, and Motivations in Autonomous Agents.

PubMed

Starzyk, Janusz A; Graham, James; Puzio, Leszek

This paper presents the development of a motivated learning (ML) agent with symbolic I/O. Our earlier work on the ML agent was enhanced, giving it autonomy for interaction with other agents. Specifically, we equipped the agent with drives and pains that establish its motivations to learn how to respond to desired and undesired events and create related abstract goals. The purpose of this paper is to explore the autonomous development of motivations and memory in agents within a simulated environment. The ML agent has been implemented in a virtual environment created within the NeoAxis game engine. Additionally, to illustrate the benefits of an ML-based agent, we compared the performance of our algorithm against various reinforcement learning (RL) algorithms in a dynamic test scenario, and demonstrated that our ML agent learns better than any of the tested RL agents.This paper presents the development of a motivated learning (ML) agent with symbolic I/O. Our earlier work on the ML agent was enhanced, giving it autonomy for interaction with other agents. Specifically, we equipped the agent with drives and pains that establish its motivations to learn how to respond to desired and undesired events and create related abstract goals. The purpose of this paper is to explore the autonomous development of motivations and memory in agents within a simulated environment. The ML agent has been implemented in a virtual environment created within the NeoAxis game engine. Additionally, to illustrate the benefits of an ML-based agent, we compared the performance of our algorithm against various reinforcement learning (RL) algorithms in a dynamic test scenario, and demonstrated that our ML agent learns better than any of the tested RL agents.

Quicker Q-Learning in Multi-Agent Systems

NASA Technical Reports Server (NTRS)

Agogino, Adrian K.; Tumer, Kagan

2005-01-01

Multi-agent learning in Markov Decisions Problems is challenging because of the presence ot two credit assignment problems: 1) How to credit an action taken at time step t for rewards received at t' greater than t; and 2) How to credit an action taken by agent i considering the system reward is a function of the actions of all the agents. The first credit assignment problem is typically addressed with temporal difference methods such as Q-learning OK TD(lambda) The second credit assi,onment problem is typically addressed either by hand-crafting reward functions that assign proper credit to an agent, or by making certain independence assumptions about an agent's state-space and reward function. To address both credit assignment problems simultaneously, we propose the Q Updates with Immediate Counterfactual Rewards-learning (QUICR-learning) designed to improve both the convergence properties and performance of Q-learning in large multi-agent problems. Instead of assuming that an agent s value function can be made independent of other agents, this method suppresses the impact of other agents using counterfactual rewards. Results on multi-agent grid-world problems over multiple topologies show that QUICR-learning can achieve up to thirty fold improvements in performance over both conventional and local Q-learning in the largest tested systems.

Rational and mechanistic perspectives on reinforcement learning.

PubMed

Chater, Nick

2009-12-01

This special issue describes important recent developments in applying reinforcement learning models to capture neural and cognitive function. But reinforcement learning, as a theoretical framework, can apply at two very different levels of description: mechanistic and rational. Reinforcement learning is often viewed in mechanistic terms--as describing the operation of aspects of an agent's cognitive and neural machinery. Yet it can also be viewed as a rational level of description, specifically, as describing a class of methods for learning from experience, using minimal background knowledge. This paper considers how rational and mechanistic perspectives differ, and what types of evidence distinguish between them. Reinforcement learning research in the cognitive and brain sciences is often implicitly committed to the mechanistic interpretation. Here the opposite view is put forward: that accounts of reinforcement learning should apply at the rational level, unless there is strong evidence for a mechanistic interpretation. Implications of this viewpoint for reinforcement-based theories in the cognitive and brain sciences are discussed.

Learning and innovative elements of strategy adoption rules expand cooperative network topologies.

PubMed

Wang, Shijun; Szalay, Máté S; Zhang, Changshui; Csermely, Peter

2008-04-09

Cooperation plays a key role in the evolution of complex systems. However, the level of cooperation extensively varies with the topology of agent networks in the widely used models of repeated games. Here we show that cooperation remains rather stable by applying the reinforcement learning strategy adoption rule, Q-learning on a variety of random, regular, small-word, scale-free and modular network models in repeated, multi-agent Prisoner's Dilemma and Hawk-Dove games. Furthermore, we found that using the above model systems other long-term learning strategy adoption rules also promote cooperation, while introducing a low level of noise (as a model of innovation) to the strategy adoption rules makes the level of cooperation less dependent on the actual network topology. Our results demonstrate that long-term learning and random elements in the strategy adoption rules, when acting together, extend the range of network topologies enabling the development of cooperation at a wider range of costs and temptations. These results suggest that a balanced duo of learning and innovation may help to preserve cooperation during the re-organization of real-world networks, and may play a prominent role in the evolution of self-organizing, complex systems.

SAN-RL: combining spreading activation networks and reinforcement learning to learn configurable behaviors

NASA Technical Reports Server (NTRS)

White, J.; Gaines, D. M.; Wilkes, M.; Kusumalnukool, K.; Thongchai, S.; Kawamura, K.

2001-01-01

This approach provides the agent with a causal structure, the spreading activation network, relating goals to the actions that can achieve those goals. This enables the agent to select actions relative to the goal priorities.

'Proactive' use of cue-context congruence for building reinforcement learning's reward function.

PubMed

Zsuga, Judit; Biro, Klara; Tajti, Gabor; Szilasi, Magdolna Emma; Papp, Csaba; Juhasz, Bela; Gesztelyi, Rudolf

2016-10-28

Reinforcement learning is a fundamental form of learning that may be formalized using the Bellman equation. Accordingly an agent determines the state value as the sum of immediate reward and of the discounted value of future states. Thus the value of state is determined by agent related attributes (action set, policy, discount factor) and the agent's knowledge of the environment embodied by the reward function and hidden environmental factors given by the transition probability. The central objective of reinforcement learning is to solve these two functions outside the agent's control either using, or not using a model. In the present paper, using the proactive model of reinforcement learning we offer insight on how the brain creates simplified representations of the environment, and how these representations are organized to support the identification of relevant stimuli and action. Furthermore, we identify neurobiological correlates of our model by suggesting that the reward and policy functions, attributes of the Bellman equitation, are built by the orbitofrontal cortex (OFC) and the anterior cingulate cortex (ACC), respectively. Based on this we propose that the OFC assesses cue-context congruence to activate the most context frame. Furthermore given the bidirectional neuroanatomical link between the OFC and model-free structures, we suggest that model-based input is incorporated into the reward prediction error (RPE) signal, and conversely RPE signal may be used to update the reward-related information of context frames and the policy underlying action selection in the OFC and ACC, respectively. Furthermore clinical implications for cognitive behavioral interventions are discussed.

Model-based reinforcement learning with dimension reduction.

PubMed

Tangkaratt, Voot; Morimoto, Jun; Sugiyama, Masashi

2016-12-01

The goal of reinforcement learning is to learn an optimal policy which controls an agent to acquire the maximum cumulative reward. The model-based reinforcement learning approach learns a transition model of the environment from data, and then derives the optimal policy using the transition model. However, learning an accurate transition model in high-dimensional environments requires a large amount of data which is difficult to obtain. To overcome this difficulty, in this paper, we propose to combine model-based reinforcement learning with the recently developed least-squares conditional entropy (LSCE) method, which simultaneously performs transition model estimation and dimension reduction. We also further extend the proposed method to imitation learning scenarios. The experimental results show that policy search combined with LSCE performs well for high-dimensional control tasks including real humanoid robot control. Copyright © 2016 Elsevier Ltd. All rights reserved.

Reciprocity Family Counseling: A Multi-Ethnic Model.

ERIC Educational Resources Information Center

Penrose, David M.

The Reciprocity Family Counseling Method involves learning principles of behavior modification including selective reinforcement, behavioral contracting, self-correction, and over-correction. Selective reinforcement refers to the recognition and modification of parent/child responses and reinforcers. Parents and children are asked to identify…

Online Bahavior Aquisition of an Agent based on Coaching as Learning Assistance

NASA Astrophysics Data System (ADS)

Hirokawa, Masakazu; Suzuki, Kenji

This paper describes a novel methodology, namely ``Coaching'', which allows humans to give a subjective evaluation to an agent in an iterative manner. This is an interactive learning method to improve the reinforcement learning by modifying a reward function dynamically according to given evaluations by a trainer and the learning situation of the agent. We demonstrate that the agent can learn different reward functions by given instructions such as ``good or bad'' by human's observation, and can also obtain a set of behavior based on the learnt reward functions through several experiments.

Deep imitation learning for 3D navigation tasks.

PubMed

Hussein, Ahmed; Elyan, Eyad; Gaber, Mohamed Medhat; Jayne, Chrisina

2018-01-01

Deep learning techniques have shown success in learning from raw high-dimensional data in various applications. While deep reinforcement learning is recently gaining popularity as a method to train intelligent agents, utilizing deep learning in imitation learning has been scarcely explored. Imitation learning can be an efficient method to teach intelligent agents by providing a set of demonstrations to learn from. However, generalizing to situations that are not represented in the demonstrations can be challenging, especially in 3D environments. In this paper, we propose a deep imitation learning method to learn navigation tasks from demonstrations in a 3D environment. The supervised policy is refined using active learning in order to generalize to unseen situations. This approach is compared to two popular deep reinforcement learning techniques: deep-Q-networks and Asynchronous actor-critic (A3C). The proposed method as well as the reinforcement learning methods employ deep convolutional neural networks and learn directly from raw visual input. Methods for combining learning from demonstrations and experience are also investigated. This combination aims to join the generalization ability of learning by experience with the efficiency of learning by imitation. The proposed methods are evaluated on 4 navigation tasks in a 3D simulated environment. Navigation tasks are a typical problem that is relevant to many real applications. They pose the challenge of requiring demonstrations of long trajectories to reach the target and only providing delayed rewards (usually terminal) to the agent. The experiments show that the proposed method can successfully learn navigation tasks from raw visual input while learning from experience methods fail to learn an effective policy. Moreover, it is shown that active learning can significantly improve the performance of the initially learned policy using a small number of active samples.

Hierarchically organized behavior and its neural foundations: A reinforcement-learning perspective

PubMed Central

Botvinick, Matthew M.; Niv, Yael; Barto, Andrew C.

2009-01-01

Research on human and animal behavior has long emphasized its hierarchical structure — the divisibility of ongoing behavior into discrete tasks, which are comprised of subtask sequences, which in turn are built of simple actions. The hierarchical structure of behavior has also been of enduring interest within neuroscience, where it has been widely considered to reflect prefrontal cortical functions. In this paper, we reexamine behavioral hierarchy and its neural substrates from the point of view of recent developments in computational reinforcement learning. Specifically, we consider a set of approaches known collectively as hierarchical reinforcement learning, which extend the reinforcement learning paradigm by allowing the learning agent to aggregate actions into reusable subroutines or skills. A close look at the components of hierarchical reinforcement learning suggests how they might map onto neural structures, in particular regions within the dorsolateral and orbital prefrontal cortex. It also suggests specific ways in which hierarchical reinforcement learning might provide a complement to existing psychological models of hierarchically structured behavior. A particularly important question that hierarchical reinforcement learning brings to the fore is that of how learning identifies new action routines that are likely to provide useful building blocks in solving a wide range of future problems. Here and at many other points, hierarchical reinforcement learning offers an appealing framework for investigating the computational and neural underpinnings of hierarchically structured behavior. PMID:18926527

Agents Control in Intelligent Learning Systems: The Case of Reactive Characteristics

ERIC Educational Resources Information Center

Laureano-Cruces, Ana Lilia; Ramirez-Rodriguez, Javier; de Arriaga, Fernando; Escarela-Perez, Rafael

2006-01-01

Intelligent learning systems (ILSs) have evolved in the last few years basically because of influences received from multi-agent architectures (MAs). Conflict resolution among agents has been a very important problem for multi-agent systems, with specific features in the case of ILSs. The literature shows that ILSs with cognitive or pedagogical…

Distributed reinforcement learning for adaptive and robust network intrusion response

NASA Astrophysics Data System (ADS)

Malialis, Kleanthis; Devlin, Sam; Kudenko, Daniel

2015-07-01

Distributed denial of service (DDoS) attacks constitute a rapidly evolving threat in the current Internet. Multiagent Router Throttling is a novel approach to defend against DDoS attacks where multiple reinforcement learning agents are installed on a set of routers and learn to rate-limit or throttle traffic towards a victim server. The focus of this paper is on online learning and scalability. We propose an approach that incorporates task decomposition, team rewards and a form of reward shaping called difference rewards. One of the novel characteristics of the proposed system is that it provides a decentralised coordinated response to the DDoS problem, thus being resilient to DDoS attacks themselves. The proposed system learns remarkably fast, thus being suitable for online learning. Furthermore, its scalability is successfully demonstrated in experiments involving 1000 learning agents. We compare our approach against a baseline and a popular state-of-the-art throttling technique from the network security literature and show that the proposed approach is more effective, adaptive to sophisticated attack rate dynamics and robust to agent failures.

Hierarchical extreme learning machine based reinforcement learning for goal localization

NASA Astrophysics Data System (ADS)

AlDahoul, Nouar; Zaw Htike, Zaw; Akmeliawati, Rini

2017-03-01

The objective of goal localization is to find the location of goals in noisy environments. Simple actions are performed to move the agent towards the goal. The goal detector should be capable of minimizing the error between the predicted locations and the true ones. Few regions need to be processed by the agent to reduce the computational effort and increase the speed of convergence. In this paper, reinforcement learning (RL) method was utilized to find optimal series of actions to localize the goal region. The visual data, a set of images, is high dimensional unstructured data and needs to be represented efficiently to get a robust detector. Different deep Reinforcement models have already been used to localize a goal but most of them take long time to learn the model. This long learning time results from the weights fine tuning stage that is applied iteratively to find an accurate model. Hierarchical Extreme Learning Machine (H-ELM) was used as a fast deep model that doesn’t fine tune the weights. In other words, hidden weights are generated randomly and output weights are calculated analytically. H-ELM algorithm was used in this work to find good features for effective representation. This paper proposes a combination of Hierarchical Extreme learning machine and Reinforcement learning to find an optimal policy directly from visual input. This combination outperforms other methods in terms of accuracy and learning speed. The simulations and results were analysed by using MATLAB.

Agent-based real-time signal coordination in congested networks.

DOT National Transportation Integrated Search

2014-01-01

This study is the continuation of a previous NEXTRANS study on agent-based reinforcement : learning methods for signal coordination in congested networks. In the previous study, the : formulation of a real-time agent-based traffic signal control in o...

Adaptive, Distributed Control of Constrained Multi-Agent Systems

NASA Technical Reports Server (NTRS)

Bieniawski, Stefan; Wolpert, David H.

2004-01-01

Product Distribution (PO) theory was recently developed as a broad framework for analyzing and optimizing distributed systems. Here we demonstrate its use for adaptive distributed control of Multi-Agent Systems (MASS), i.e., for distributed stochastic optimization using MAS s. First we review one motivation of PD theory, as the information-theoretic extension of conventional full-rationality game theory to the case of bounded rational agents. In this extension the equilibrium of the game is the optimizer of a Lagrangian of the (Probability dist&&on on the joint state of the agents. When the game in question is a team game with constraints, that equilibrium optimizes the expected value of the team game utility, subject to those constraints. One common way to find that equilibrium is to have each agent run a Reinforcement Learning (E) algorithm. PD theory reveals this to be a particular type of search algorithm for minimizing the Lagrangian. Typically that algorithm i s quite inefficient. A more principled alternative is to use a variant of Newton's method to minimize the Lagrangian. Here we compare this alternative to RL-based search in three sets of computer experiments. These are the N Queen s problem and bin-packing problem from the optimization literature, and the Bar problem from the distributed RL literature. Our results confirm that the PD-theory-based approach outperforms the RL-based scheme in all three domains.

Construction of a Learning Agent Handling Its Rewards According to Environmental Situations

NASA Astrophysics Data System (ADS)

Moriyama, Koichi; Numao, Masayuki

The authors aim at constructing an agent which learns appropriate actions in a Multi-Agent environment with and without social dilemmas. For this aim, the agent must have nonrationality that makes it give up its own profit when it should do that. Since there are many studies on rational learning that brings more and more profit, it is desirable to utilize them for constructing the agent. Therefore, we use a reward-handling manner that makes internal evaluation from the agent's rewards, and then the agent learns actions by a rational learning method with the internal evaluation. If the agent has only a fixed manner, however, it does not act well in the environment with and without dilemmas. Thus, the authors equip the agent with several reward-handling manners and criteria for selecting an effective one for the environmental situation. In the case of humans, what generates the internal evaluation is usually called emotion. Hence, this study also aims at throwing light on emotional activities of humans from a constructive view. In this paper, we divide a Multi-Agent environment into three situations and construct an agent having the reward-handling manners and the criteria. We observe that the agent acts well in all the three Multi-Agent situations composed of homogeneous agents.

Neural computations underlying inverse reinforcement learning in the human brain

PubMed Central

Pauli, Wolfgang M; Bossaerts, Peter; O'Doherty, John

2017-01-01

In inverse reinforcement learning an observer infers the reward distribution available for actions in the environment solely through observing the actions implemented by another agent. To address whether this computational process is implemented in the human brain, participants underwent fMRI while learning about slot machines yielding hidden preferred and non-preferred food outcomes with varying probabilities, through observing the repeated slot choices of agents with similar and dissimilar food preferences. Using formal model comparison, we found that participants implemented inverse RL as opposed to a simple imitation strategy, in which the actions of the other agent are copied instead of inferring the underlying reward structure of the decision problem. Our computational fMRI analysis revealed that anterior dorsomedial prefrontal cortex encoded inferences about action-values within the value space of the agent as opposed to that of the observer, demonstrating that inverse RL is an abstract cognitive process divorceable from the values and concerns of the observer him/herself. PMID:29083301

Multi Agent Reward Analysis for Learning in Noisy Domains

NASA Technical Reports Server (NTRS)

Tumer, Kagan; Agogino, Adrian K.

2005-01-01

In many multi agent learning problems, it is difficult to determine, a priori, the agent reward structure that will lead to good performance. This problem is particularly pronounced in continuous, noisy domains ill-suited to simple table backup schemes commonly used in TD(lambda)/Q-learning. In this paper, we present a new reward evaluation method that allows the tradeoff between coordination among the agents and the difficulty of the learning problem each agent faces to be visualized. This method is independent of the learning algorithm and is only a function of the problem domain and the agents reward structure. We then use this reward efficiency visualization method to determine an effective reward without performing extensive simulations. We test this method in both a static and a dynamic multi-rover learning domain where the agents have continuous state spaces and where their actions are noisy (e.g., the agents movement decisions are not always carried out properly). Our results show that in the more difficult dynamic domain, the reward efficiency visualization method provides a two order of magnitude speedup in selecting a good reward. Most importantly it allows one to quickly create and verify rewards tailored to the observational limitations of the domain.

A Two-Stage Multi-Agent Based Assessment Approach to Enhance Students' Learning Motivation through Negotiated Skills Assessment

ERIC Educational Resources Information Center

Chadli, Abdelhafid; Bendella, Fatima; Tranvouez, Erwan

2015-01-01

In this paper we present an Agent-based evaluation approach in a context of Multi-agent simulation learning systems. Our evaluation model is based on a two stage assessment approach: (1) a Distributed skill evaluation combining agents and fuzzy sets theory; and (2) a Negotiation based evaluation of students' performance during a training…

Reinforcement learning algorithms for robotic navigation in dynamic environments.

PubMed

Yen, Gary G; Hickey, Travis W

2004-04-01

The purpose of this study was to examine improvements to reinforcement learning (RL) algorithms in order to successfully interact within dynamic environments. The scope of the research was that of RL algorithms as applied to robotic navigation. Proposed improvements include: addition of a forgetting mechanism, use of feature based state inputs, and hierarchical structuring of an RL agent. Simulations were performed to evaluate the individual merits and flaws of each proposal, to compare proposed methods to prior established methods, and to compare proposed methods to theoretically optimal solutions. Incorporation of a forgetting mechanism did considerably improve the learning times of RL agents in a dynamic environment. However, direct implementation of a feature-based RL agent did not result in any performance enhancements, as pure feature-based navigation results in a lack of positional awareness, and the inability of the agent to determine the location of the goal state. Inclusion of a hierarchical structure in an RL agent resulted in significantly improved performance, specifically when one layer of the hierarchy included a feature-based agent for obstacle avoidance, and a standard RL agent for global navigation. In summary, the inclusion of a forgetting mechanism, and the use of a hierarchically structured RL agent offer substantially increased performance when compared to traditional RL agents navigating in a dynamic environment.

Designing Agent Utilities for Coordinated, Scalable and Robust Multi-Agent Systems

NASA Technical Reports Server (NTRS)

Tumer, Kagan

2005-01-01

Coordinating the behavior of a large number of agents to achieve a system level goal poses unique design challenges. In particular, problems of scaling (number of agents in the thousands to tens of thousands), observability (agents have limited sensing capabilities), and robustness (the agents are unreliable) make it impossible to simply apply methods developed for small multi-agent systems composed of reliable agents. To address these problems, we present an approach based on deriving agent goals that are aligned with the overall system goal, and can be computed using information readily available to the agents. Then, each agent uses a simple reinforcement learning algorithm to pursue its own goals. Because of the way in which those goals are derived, there is no need to use difficult to scale external mechanisms to force collaboration or coordination among the agents, or to ensure that agents actively attempt to appropriate the tasks of agents that suffered failures. To present these results in a concrete setting, we focus on the problem of finding the sub-set of a set of imperfect devices that results in the best aggregate device. This is a large distributed agent coordination problem where each agent (e.g., device) needs to determine whether to be part of the aggregate device. Our results show that the approach proposed in this work provides improvements of over an order of magnitude over both traditional search methods and traditional multi-agent methods. Furthermore, the results show that even in extreme cases of agent failures (i.e., half the agents failed midway through the simulation) the system's performance degrades gracefully and still outperforms a failure-free and centralized search algorithm. The results also show that the gains increase as the size of the system (e.g., number of agents) increases. This latter result is particularly encouraging and suggests that this method is ideally suited for domains where the number of agents is currently in the thousands and will reach tens or hundreds of thousands in the near future.

Robust reinforcement learning.

PubMed

Morimoto, Jun; Doya, Kenji

2005-02-01

This letter proposes a new reinforcement learning (RL) paradigm that explicitly takes into account input disturbance as well as modeling errors. The use of environmental models in RL is quite popular for both offline learning using simulations and for online action planning. However, the difference between the model and the real environment can lead to unpredictable, and often unwanted, results. Based on the theory of H(infinity) control, we consider a differential game in which a "disturbing" agent tries to make the worst possible disturbance while a "control" agent tries to make the best control input. The problem is formulated as finding a min-max solution of a value function that takes into account the amount of the reward and the norm of the disturbance. We derive online learning algorithms for estimating the value function and for calculating the worst disturbance and the best control in reference to the value function. We tested the paradigm, which we call robust reinforcement learning (RRL), on the control task of an inverted pendulum. In the linear domain, the policy and the value function learned by online algorithms coincided with those derived analytically by the linear H(infinity) control theory. For a fully nonlinear swing-up task, RRL achieved robust performance with changes in the pendulum weight and friction, while a standard reinforcement learning algorithm could not deal with these changes. We also applied RRL to the cart-pole swing-up task, and a robust swing-up policy was acquired.

Self-Learning Power Control in Wireless Sensor Networks.

PubMed

Chincoli, Michele; Liotta, Antonio

2018-01-27

Current trends in interconnecting myriad smart objects to monetize on Internet of Things applications have led to high-density communications in wireless sensor networks. This aggravates the already over-congested unlicensed radio bands, calling for new mechanisms to improve spectrum management and energy efficiency, such as transmission power control. Existing protocols are based on simplistic heuristics that often approach interference problems (i.e., packet loss, delay and energy waste) by increasing power, leading to detrimental results. The scope of this work is to investigate how machine learning may be used to bring wireless nodes to the lowest possible transmission power level and, in turn, to respect the quality requirements of the overall network. Lowering transmission power has benefits in terms of both energy consumption and interference. We propose a protocol of transmission power control through a reinforcement learning process that we have set in a multi-agent system. The agents are independent learners using the same exploration strategy and reward structure, leading to an overall cooperative network. The simulation results show that the system converges to an equilibrium where each node transmits at the minimum power while respecting high packet reception ratio constraints. Consequently, the system benefits from low energy consumption and packet delay.

Self-Learning Power Control in Wireless Sensor Networks

PubMed Central

Liotta, Antonio

2018-01-01

Current trends in interconnecting myriad smart objects to monetize on Internet of Things applications have led to high-density communications in wireless sensor networks. This aggravates the already over-congested unlicensed radio bands, calling for new mechanisms to improve spectrum management and energy efficiency, such as transmission power control. Existing protocols are based on simplistic heuristics that often approach interference problems (i.e., packet loss, delay and energy waste) by increasing power, leading to detrimental results. The scope of this work is to investigate how machine learning may be used to bring wireless nodes to the lowest possible transmission power level and, in turn, to respect the quality requirements of the overall network. Lowering transmission power has benefits in terms of both energy consumption and interference. We propose a protocol of transmission power control through a reinforcement learning process that we have set in a multi-agent system. The agents are independent learners using the same exploration strategy and reward structure, leading to an overall cooperative network. The simulation results show that the system converges to an equilibrium where each node transmits at the minimum power while respecting high packet reception ratio constraints. Consequently, the system benefits from low energy consumption and packet delay. PMID:29382072

Hybrid learning in signalling games

NASA Astrophysics Data System (ADS)

Barrett, Jeffrey A.; Cochran, Calvin T.; Huttegger, Simon; Fujiwara, Naoki

2017-09-01

Lewis-Skyrms signalling games have been studied under a variety of low-rationality learning dynamics. Reinforcement dynamics are stable but slow and prone to evolving suboptimal signalling conventions. A low-inertia trial-and-error dynamical like win-stay/lose-randomise is fast and reliable at finding perfect signalling conventions but unstable in the context of noise or agent error. Here we consider a low-rationality hybrid of reinforcement and win-stay/lose-randomise learning that exhibits the virtues of both. This hybrid dynamics is reliable, stable and exceptionally fast.

A Distributed Intelligent E-Learning System

ERIC Educational Resources Information Center

Kristensen, Terje

2016-01-01

An E-learning system based on a multi-agent (MAS) architecture combined with the Dynamic Content Manager (DCM) model of E-learning, is presented. We discuss the benefits of using such a multi-agent architecture. Finally, the MAS architecture is compared with a pure service-oriented architecture (SOA). This MAS architecture may also be used within…

Reinforcement learning: Solving two case studies

NASA Astrophysics Data System (ADS)

Duarte, Ana Filipa; Silva, Pedro; dos Santos, Cristina Peixoto

2012-09-01

Reinforcement Learning algorithms offer interesting features for the control of autonomous systems, such as the ability to learn from direct interaction with the environment, and the use of a simple reward signalas opposed to the input-outputs pairsused in classic supervised learning. The reward signal indicates the success of failure of the actions executed by the agent in the environment. In this work, are described RL algorithmsapplied to two case studies: the Crawler robot and the widely known inverted pendulum. We explore RL capabilities to autonomously learn a basic locomotion pattern in the Crawler, andapproach the balancing problem of biped locomotion using the inverted pendulum.

FMRQ-A Multiagent Reinforcement Learning Algorithm for Fully Cooperative Tasks.

PubMed

Zhang, Zhen; Zhao, Dongbin; Gao, Junwei; Wang, Dongqing; Dai, Yujie

2017-06-01

In this paper, we propose a multiagent reinforcement learning algorithm dealing with fully cooperative tasks. The algorithm is called frequency of the maximum reward Q-learning (FMRQ). FMRQ aims to achieve one of the optimal Nash equilibria so as to optimize the performance index in multiagent systems. The frequency of obtaining the highest global immediate reward instead of immediate reward is used as the reinforcement signal. With FMRQ each agent does not need the observation of the other agents' actions and only shares its state and reward at each step. We validate FMRQ through case studies of repeated games: four cases of two-player two-action and one case of three-player two-action. It is demonstrated that FMRQ can converge to one of the optimal Nash equilibria in these cases. Moreover, comparison experiments on tasks with multiple states and finite steps are conducted. One is box-pushing and the other one is distributed sensor network problem. Experimental results show that the proposed algorithm outperforms others with higher performance.

Incremental learning of skill collections based on intrinsic motivation

PubMed Central

Metzen, Jan H.; Kirchner, Frank

2013-01-01

Life-long learning of reusable, versatile skills is a key prerequisite for embodied agents that act in a complex, dynamic environment and are faced with different tasks over their lifetime. We address the question of how an agent can learn useful skills efficiently during a developmental period, i.e., when no task is imposed on him and no external reward signal is provided. Learning of skills in a developmental period needs to be incremental and self-motivated. We propose a new incremental, task-independent skill discovery approach that is suited for continuous domains. Furthermore, the agent learns specific skills based on intrinsic motivation mechanisms that determine on which skills learning is focused at a given point in time. We evaluate the approach in a reinforcement learning setup in two continuous domains with complex dynamics. We show that an intrinsically motivated, skill learning agent outperforms an agent which learns task solutions from scratch. Furthermore, we compare different intrinsic motivation mechanisms and how efficiently they make use of the agent's developmental period. PMID:23898265

Model-Free control performance improvement using virtual reference feedback tuning and reinforcement Q-learning

NASA Astrophysics Data System (ADS)

Radac, Mircea-Bogdan; Precup, Radu-Emil; Roman, Raul-Cristian

2017-04-01

This paper proposes the combination of two model-free controller tuning techniques, namely linear virtual reference feedback tuning (VRFT) and nonlinear state-feedback Q-learning, referred to as a new mixed VRFT-Q learning approach. VRFT is first used to find stabilising feedback controller using input-output experimental data from the process in a model reference tracking setting. Reinforcement Q-learning is next applied in the same setting using input-state experimental data collected under perturbed VRFT to ensure good exploration. The Q-learning controller learned with a batch fitted Q iteration algorithm uses two neural networks, one for the Q-function estimator and one for the controller, respectively. The VRFT-Q learning approach is validated on position control of a two-degrees-of-motion open-loop stable multi input-multi output (MIMO) aerodynamic system (AS). Extensive simulations for the two independent control channels of the MIMO AS show that the Q-learning controllers clearly improve performance over the VRFT controllers.

The cerebellum: a neural system for the study of reinforcement learning.

PubMed

Swain, Rodney A; Kerr, Abigail L; Thompson, Richard F

2011-01-01

In its strictest application, the term "reinforcement learning" refers to a computational approach to learning in which an agent (often a machine) interacts with a mutable environment to maximize reward through trial and error. The approach borrows essentials from several fields, most notably Computer Science, Behavioral Neuroscience, and Psychology. At the most basic level, a neural system capable of mediating reinforcement learning must be able to acquire sensory information about the external environment and internal milieu (either directly or through connectivities with other brain regions), must be able to select a behavior to be executed, and must be capable of providing evaluative feedback about the success of that behavior. Given that Psychology informs us that reinforcers, both positive and negative, are stimuli or consequences that increase the probability that the immediately antecedent behavior will be repeated and that reinforcer strength or viability is modulated by the organism's past experience with the reinforcer, its affect, and even the state of its muscles (e.g., eyes open or closed); it is the case that any neural system that supports reinforcement learning must also be sensitive to these same considerations. Once learning is established, such a neural system must finally be able to maintain continued response expression and prevent response drift. In this report, we examine both historical and recent evidence that the cerebellum satisfies all of these requirements. While we report evidence from a variety of learning paradigms, the majority of our discussion will focus on classical conditioning of the rabbit eye blink response as an ideal model system for the study of reinforcement and reinforcement learning.

Human Aided Reinforcement Learning in Complex Environments

DTIC Science & Technology

learn to solve tasks through a trial -and- error process. As an agent takes ...task faster andmore accurately, a human expert can be added to the system to guide an agent in solving the task. This project seeks to expand on current...theenvironment, which works particularly well for reactive tasks . In more complex tasks , these systems do not work as intended. The manipulation

Reinforcement Learning with Orthonormal Basis Adaptation Based on Activity-Oriented Index Allocation

NASA Astrophysics Data System (ADS)

Satoh, Hideki

An orthonormal basis adaptation method for function approximation was developed and applied to reinforcement learning with multi-dimensional continuous state space. First, a basis used for linear function approximation of a control function is set to an orthonormal basis. Next, basis elements with small activities are replaced with other candidate elements as learning progresses. As this replacement is repeated, the number of basis elements with large activities increases. Example chaos control problems for multiple logistic maps were solved, demonstrating that the method for adapting an orthonormal basis can modify a basis while holding the orthonormality in accordance with changes in the environment to improve the performance of reinforcement learning and to eliminate the adverse effects of redundant noisy states.

QUICR-learning for Multi-Agent Coordination

NASA Technical Reports Server (NTRS)

Agogino, Adrian K.; Tumer, Kagan

2006-01-01

Coordinating multiple agents that need to perform a sequence of actions to maximize a system level reward requires solving two distinct credit assignment problems. First, credit must be assigned for an action taken at time step t that results in a reward at time step t > t. Second, credit must be assigned for the contribution of agent i to the overall system performance. The first credit assignment problem is typically addressed with temporal difference methods such as Q-learning. The second credit assignment problem is typically addressed by creating custom reward functions. To address both credit assignment problems simultaneously, we propose the "Q Updates with Immediate Counterfactual Rewards-learning" (QUICR-learning) designed to improve both the convergence properties and performance of Q-learning in large multi-agent problems. QUICR-learning is based on previous work on single-time-step counterfactual rewards described by the collectives framework. Results on a traffic congestion problem shows that QUICR-learning is significantly better than a Q-learner using collectives-based (single-time-step counterfactual) rewards. In addition QUICR-learning provides significant gains over conventional and local Q-learning. Additional results on a multi-agent grid-world problem show that the improvements due to QUICR-learning are not domain specific and can provide up to a ten fold increase in performance over existing methods.

Multi Agent Systems with Symbiotic Learning and Evolution using GNP

NASA Astrophysics Data System (ADS)

Eguchi, Toru; Hirasawa, Kotaro; Hu, Jinglu; Murata, Junichi

Recently, various attempts relevant to Multi Agent Systems (MAS) which is one of the most promising systems based on Distributed Artificial Intelligence have been studied to control large and complicated systems efficiently. In these trends of MAS, Multi Agent Systems with Symbiotic Learning and Evolution named Masbiole has been proposed. In Masbiole, symbiotic phenomena among creatures are considered in the process of learning and evolution of MAS. So we can expect more flexible and sophisticated solutions than conventional MAS. In this paper, we apply Masbiole to Iterative Prisoner’s Dilemma Games (IPD Games) using Genetic Network Programming (GNP) which is a newly developed evolutionary computation method for constituting agents. Some characteristics of Masbiole using GNP in IPD Games are clarified.

The "proactive" model of learning: Integrative framework for model-free and model-based reinforcement learning utilizing the associative learning-based proactive brain concept.

PubMed

Zsuga, Judit; Biro, Klara; Papp, Csaba; Tajti, Gabor; Gesztelyi, Rudolf

2016-02-01

Reinforcement learning (RL) is a powerful concept underlying forms of associative learning governed by the use of a scalar reward signal, with learning taking place if expectations are violated. RL may be assessed using model-based and model-free approaches. Model-based reinforcement learning involves the amygdala, the hippocampus, and the orbitofrontal cortex (OFC). The model-free system involves the pedunculopontine-tegmental nucleus (PPTgN), the ventral tegmental area (VTA) and the ventral striatum (VS). Based on the functional connectivity of VS, model-free and model based RL systems center on the VS that by integrating model-free signals (received as reward prediction error) and model-based reward related input computes value. Using the concept of reinforcement learning agent we propose that the VS serves as the value function component of the RL agent. Regarding the model utilized for model-based computations we turned to the proactive brain concept, which offers an ubiquitous function for the default network based on its great functional overlap with contextual associative areas. Hence, by means of the default network the brain continuously organizes its environment into context frames enabling the formulation of analogy-based association that are turned into predictions of what to expect. The OFC integrates reward-related information into context frames upon computing reward expectation by compiling stimulus-reward and context-reward information offered by the amygdala and hippocampus, respectively. Furthermore we suggest that the integration of model-based expectations regarding reward into the value signal is further supported by the efferent of the OFC that reach structures canonical for model-free learning (e.g., the PPTgN, VTA, and VS). (c) 2016 APA, all rights reserved).

TSI-Enhanced Pedagogical Agents to Engage Learners in Virtual Worlds

ERIC Educational Resources Information Center

Leung, Steve; Virwaney, Sandeep; Lin, Fuhua; Armstrong, AJ; Dubbelboer, Adien

2013-01-01

Building pedagogical applications in virtual worlds is a multi-disciplinary endeavor that involves learning theories, application development framework, and mediated communication theories. This paper presents a project that integrates game-based learning, multi-agent system architecture (MAS), and the theory of Transformed Social Interaction…

Curiosity driven reinforcement learning for motion planning on humanoids

PubMed Central

Frank, Mikhail; Leitner, Jürgen; Stollenga, Marijn; Förster, Alexander; Schmidhuber, Jürgen

2014-01-01

Most previous work on artificial curiosity (AC) and intrinsic motivation focuses on basic concepts and theory. Experimental results are generally limited to toy scenarios, such as navigation in a simulated maze, or control of a simple mechanical system with one or two degrees of freedom. To study AC in a more realistic setting, we embody a curious agent in the complex iCub humanoid robot. Our novel reinforcement learning (RL) framework consists of a state-of-the-art, low-level, reactive control layer, which controls the iCub while respecting constraints, and a high-level curious agent, which explores the iCub's state-action space through information gain maximization, learning a world model from experience, controlling the actual iCub hardware in real-time. To the best of our knowledge, this is the first ever embodied, curious agent for real-time motion planning on a humanoid. We demonstrate that it can learn compact Markov models to represent large regions of the iCub's configuration space, and that the iCub explores intelligently, showing interest in its physical constraints as well as in objects it finds in its environment. PMID:24432001

A reinforcement learning model of joy, distress, hope and fear

NASA Astrophysics Data System (ADS)

Broekens, Joost; Jacobs, Elmer; Jonker, Catholijn M.

2015-07-01

In this paper we computationally study the relation between adaptive behaviour and emotion. Using the reinforcement learning framework, we propose that learned state utility, ?, models fear (negative) and hope (positive) based on the fact that both signals are about anticipation of loss or gain. Further, we propose that joy/distress is a signal similar to the error signal. We present agent-based simulation experiments that show that this model replicates psychological and behavioural dynamics of emotion. This work distinguishes itself by assessing the dynamics of emotion in an adaptive agent framework - coupling it to the literature on habituation, development, extinction and hope theory. Our results support the idea that the function of emotion is to provide a complex feedback signal for an organism to adapt its behaviour. Our work is relevant for understanding the relation between emotion and adaptation in animals, as well as for human-robot interaction, in particular how emotional signals can be used to communicate between adaptive agents and humans.

Global adaptation in networks of selfish components: emergent associative memory at the system scale.

PubMed

Watson, Richard A; Mills, Rob; Buckley, C L

2011-01-01

In some circumstances complex adaptive systems composed of numerous self-interested agents can self-organize into structures that enhance global adaptation, efficiency, or function. However, the general conditions for such an outcome are poorly understood and present a fundamental open question for domains as varied as ecology, sociology, economics, organismic biology, and technological infrastructure design. In contrast, sufficient conditions for artificial neural networks to form structures that perform collective computational processes such as associative memory/recall, classification, generalization, and optimization are well understood. Such global functions within a single agent or organism are not wholly surprising, since the mechanisms (e.g., Hebbian learning) that create these neural organizations may be selected for this purpose; but agents in a multi-agent system have no obvious reason to adhere to such a structuring protocol or produce such global behaviors when acting from individual self-interest. However, Hebbian learning is actually a very simple and fully distributed habituation or positive feedback principle. Here we show that when self-interested agents can modify how they are affected by other agents (e.g., when they can influence which other agents they interact with), then, in adapting these inter-agent relationships to maximize their own utility, they will necessarily alter them in a manner homologous with Hebbian learning. Multi-agent systems with adaptable relationships will thereby exhibit the same system-level behaviors as neural networks under Hebbian learning. For example, improved global efficiency in multi-agent systems can be explained by the inherent ability of associative memory to generalize by idealizing stored patterns and/or creating new combinations of subpatterns. Thus distributed multi-agent systems can spontaneously exhibit adaptive global behaviors in the same sense, and by the same mechanism, as with the organizational principles familiar in connectionist models of organismic learning.

A Multi-Agent System for Intelligent Online Education.

ERIC Educational Resources Information Center

O'Riordan, Colm; Griffith, Josephine

1999-01-01

Describes the system architecture of an intelligent Web-based education system that includes user modeling agents, information filtering agents for automatic information gathering, and the multi-agent interaction. Discusses information management; user interaction; support for collaborative peer-peer learning; implementation; testing; and future…

Characterizing Reinforcement Learning Methods through Parameterized Learning Problems

DTIC Science & Technology

2011-06-03

extraneous. The agent could potentially adapt these representational aspects by applying methods from feature selection ( Kolter and Ng, 2009; Petrik et al...611–616. AAAI Press. Kolter , J. Z. and Ng, A. Y. (2009). Regularization and feature selection in least-squares temporal difference learning. In A. P

Modeling Humans as Reinforcement Learners: How to Predict Human Behavior in Multi-Stage Games

NASA Technical Reports Server (NTRS)

Lee, Ritchie; Wolpert, David H.; Backhaus, Scott; Bent, Russell; Bono, James; Tracey, Brendan

2011-01-01

This paper introduces a novel framework for modeling interacting humans in a multi-stage game environment by combining concepts from game theory and reinforcement learning. The proposed model has the following desirable characteristics: (1) Bounded rational players, (2) strategic (i.e., players account for one anothers reward functions), and (3) is computationally feasible even on moderately large real-world systems. To do this we extend level-K reasoning to policy space to, for the first time, be able to handle multiple time steps. This allows us to decompose the problem into a series of smaller ones where we can apply standard reinforcement learning algorithms. We investigate these ideas in a cyber-battle scenario over a smart power grid and discuss the relationship between the behavior predicted by our model and what one might expect of real human defenders and attackers.

Observer-based distributed adaptive iterative learning control for linear multi-agent systems

NASA Astrophysics Data System (ADS)

Li, Jinsha; Liu, Sanyang; Li, Junmin

2017-10-01

This paper investigates the consensus problem for linear multi-agent systems from the viewpoint of two-dimensional systems when the state information of each agent is not available. Observer-based fully distributed adaptive iterative learning protocol is designed in this paper. A local observer is designed for each agent and it is shown that without using any global information about the communication graph, all agents achieve consensus perfectly for all undirected connected communication graph when the number of iterations tends to infinity. The Lyapunov-like energy function is employed to facilitate the learning protocol design and property analysis. Finally, simulation example is given to illustrate the theoretical analysis.

Time-Extended Payoffs for Collectives of Autonomous Agents

NASA Technical Reports Server (NTRS)

Tumer, Kagan; Agogino, Adrian K.

2002-01-01

A collective is a set of self-interested agents which try to maximize their own utilities, along with a a well-defined, time-extended world utility function which rates the performance of the entire system. In this paper, we use theory of collectives to design time-extended payoff utilities for agents that are both aligned with the world utility, and are "learnable", i.e., the agents can readily see how their behavior affects their utility. We show that in systems where each agent aims to optimize such payoff functions, coordination arises as a byproduct of the agents selfishly pursuing their own goals. A game theoretic analysis shows that such payoff functions have the net effect of aligning the Nash equilibrium, Pareto optimal solution and world utility optimum, thus eliminating undesirable behavior such as agents working at cross-purposes. We then apply collective-based payoff functions to the token collection in a gridworld problem where agents need to optimize the aggregate value of tokens collected across an episode of finite duration (i.e., an abstracted version of rovers on Mars collecting scientifically interesting rock samples, subject to power limitations). We show that, regardless of the initial token distribution, reinforcement learning agents using collective-based payoff functions significantly outperform both natural extensions of single agent algorithms and global reinforcement learning solutions based on "team games".

Learning Natural Selection in 4th Grade with Multi-Agent-Based Computational Models

ERIC Educational Resources Information Center

Dickes, Amanda Catherine; Sengupta, Pratim

2013-01-01

In this paper, we investigate how elementary school students develop multi-level explanations of population dynamics in a simple predator-prey ecosystem, through scaffolded interactions with a multi-agent-based computational model (MABM). The term "agent" in an MABM indicates individual computational objects or actors (e.g., cars), and these…

Improving Robot Motor Learning with Negatively Valenced Reinforcement Signals

PubMed Central

Navarro-Guerrero, Nicolás; Lowe, Robert J.; Wermter, Stefan

2017-01-01

Both nociception and punishment signals have been used in robotics. However, the potential for using these negatively valenced types of reinforcement learning signals for robot learning has not been exploited in detail yet. Nociceptive signals are primarily used as triggers of preprogrammed action sequences. Punishment signals are typically disembodied, i.e., with no or little relation to the agent-intrinsic limitations, and they are often used to impose behavioral constraints. Here, we provide an alternative approach for nociceptive signals as drivers of learning rather than simple triggers of preprogrammed behavior. Explicitly, we use nociception to expand the state space while we use punishment as a negative reinforcement learning signal. We compare the performance—in terms of task error, the amount of perceived nociception, and length of learned action sequences—of different neural networks imbued with punishment-based reinforcement signals for inverse kinematic learning. We contrast the performance of a version of the neural network that receives nociceptive inputs to that without such a process. Furthermore, we provide evidence that nociception can improve learning—making the algorithm more robust against network initializations—as well as behavioral performance by reducing the task error, perceived nociception, and length of learned action sequences. Moreover, we provide evidence that punishment, at least as typically used within reinforcement learning applications, may be detrimental in all relevant metrics. PMID:28420976

Reinforcement Learning in a Nonstationary Environment: The El Farol Problem

NASA Technical Reports Server (NTRS)

Bell, Ann Maria

1999-01-01

This paper examines the performance of simple learning rules in a complex adaptive system based on a coordination problem modeled on the El Farol problem. The key features of the El Farol problem are that it typically involves a medium number of agents and that agents' pay-off functions have a discontinuous response to increased congestion. First we consider a single adaptive agent facing a stationary environment. We demonstrate that the simple learning rules proposed by Roth and Er'ev can be extremely sensitive to small changes in the initial conditions and that events early in a simulation can affect the performance of the rule over a relatively long time horizon. In contrast, a reinforcement learning rule based on standard practice in the computer science literature converges rapidly and robustly. The situation is reversed when multiple adaptive agents interact: the RE algorithms often converge rapidly to a stable average aggregate attendance despite the slow and erratic behavior of individual learners, while the CS based learners frequently over-attend in the early and intermediate terms. The symmetric mixed strategy equilibria is unstable: all three learning rules ultimately tend towards pure strategies or stabilize in the medium term at non-equilibrium probabilities of attendance. The brittleness of the algorithms in different contexts emphasize the importance of thorough and thoughtful examination of simulation-based results.

Multi-issue Agent Negotiation Based on Fairness

NASA Astrophysics Data System (ADS)

Zuo, Baohe; Zheng, Sue; Wu, Hong

Agent-based e-commerce service has become a hotspot now. How to make the agent negotiation process quickly and high-efficiently is the main research direction of this area. In the multi-issue model, MAUT(Multi-attribute Utility Theory) or its derived theory usually consider little about the fairness of both negotiators. This work presents a general model of agent negotiation which considered the satisfaction of both negotiators via autonomous learning. The model can evaluate offers from the opponent agent based on the satisfaction degree, learn online to get the opponent's knowledge from interactive instances of history and negotiation of this time, make concessions dynamically based on fair object. Through building the optimal negotiation model, the bilateral negotiation achieved a higher efficiency and fairer deal.

Context transfer in reinforcement learning using action-value functions.

PubMed

Mousavi, Amin; Nadjar Araabi, Babak; Nili Ahmadabadi, Majid

2014-01-01

This paper discusses the notion of context transfer in reinforcement learning tasks. Context transfer, as defined in this paper, implies knowledge transfer between source and target tasks that share the same environment dynamics and reward function but have different states or action spaces. In other words, the agents learn the same task while using different sensors and actuators. This requires the existence of an underlying common Markov decision process (MDP) to which all the agents' MDPs can be mapped. This is formulated in terms of the notion of MDP homomorphism. The learning framework is Q-learning. To transfer the knowledge between these tasks, the feature space is used as a translator and is expressed as a partial mapping between the state-action spaces of different tasks. The Q-values learned during the learning process of the source tasks are mapped to the sets of Q-values for the target task. These transferred Q-values are merged together and used to initialize the learning process of the target task. An interval-based approach is used to represent and merge the knowledge of the source tasks. Empirical results show that the transferred initialization can be beneficial to the learning process of the target task.

Context Transfer in Reinforcement Learning Using Action-Value Functions

PubMed Central

Mousavi, Amin; Nadjar Araabi, Babak; Nili Ahmadabadi, Majid

2014-01-01

This paper discusses the notion of context transfer in reinforcement learning tasks. Context transfer, as defined in this paper, implies knowledge transfer between source and target tasks that share the same environment dynamics and reward function but have different states or action spaces. In other words, the agents learn the same task while using different sensors and actuators. This requires the existence of an underlying common Markov decision process (MDP) to which all the agents' MDPs can be mapped. This is formulated in terms of the notion of MDP homomorphism. The learning framework is Q-learning. To transfer the knowledge between these tasks, the feature space is used as a translator and is expressed as a partial mapping between the state-action spaces of different tasks. The Q-values learned during the learning process of the source tasks are mapped to the sets of Q-values for the target task. These transferred Q-values are merged together and used to initialize the learning process of the target task. An interval-based approach is used to represent and merge the knowledge of the source tasks. Empirical results show that the transferred initialization can be beneficial to the learning process of the target task. PMID:25610457

Goal-oriented robot navigation learning using a multi-scale space representation.

PubMed

Llofriu, M; Tejera, G; Contreras, M; Pelc, T; Fellous, J M; Weitzenfeld, A

2015-12-01

There has been extensive research in recent years on the multi-scale nature of hippocampal place cells and entorhinal grid cells encoding which led to many speculations on their role in spatial cognition. In this paper we focus on the multi-scale nature of place cells and how they contribute to faster learning during goal-oriented navigation when compared to a spatial cognition system composed of single scale place cells. The task consists of a circular arena with a fixed goal location, in which a robot is trained to find the shortest path to the goal after a number of learning trials. Synaptic connections are modified using a reinforcement learning paradigm adapted to the place cells multi-scale architecture. The model is evaluated in both simulation and physical robots. We find that larger scale and combined multi-scale representations favor goal-oriented navigation task learning. Copyright © 2015 Elsevier Ltd. All rights reserved.

Safe Exploration Algorithms for Reinforcement Learning Controllers.

PubMed

Mannucci, Tommaso; van Kampen, Erik-Jan; de Visser, Cornelis; Chu, Qiping

2018-04-01

Self-learning approaches, such as reinforcement learning, offer new possibilities for autonomous control of uncertain or time-varying systems. However, exploring an unknown environment under limited prediction capabilities is a challenge for a learning agent. If the environment is dangerous, free exploration can result in physical damage or in an otherwise unacceptable behavior. With respect to existing methods, the main contribution of this paper is the definition of a new approach that does not require global safety functions, nor specific formulations of the dynamics or of the environment, but relies on interval estimation of the dynamics of the agent during the exploration phase, assuming a limited capability of the agent to perceive the presence of incoming fatal states. Two algorithms are presented with this approach. The first is the Safety Handling Exploration with Risk Perception Algorithm (SHERPA), which provides safety by individuating temporary safety functions, called backups. SHERPA is shown in a simulated, simplified quadrotor task, for which dangerous states are avoided. The second algorithm, denominated OptiSHERPA, can safely handle more dynamically complex systems for which SHERPA is not sufficient through the use of safety metrics. An application of OptiSHERPA is simulated on an aircraft altitude control task.

Stochastic abstract policies: generalizing knowledge to improve reinforcement learning.

PubMed

Koga, Marcelo L; Freire, Valdinei; Costa, Anna H R

2015-01-01

Reinforcement learning (RL) enables an agent to learn behavior by acquiring experience through trial-and-error interactions with a dynamic environment. However, knowledge is usually built from scratch and learning to behave may take a long time. Here, we improve the learning performance by leveraging prior knowledge; that is, the learner shows proper behavior from the beginning of a target task, using the knowledge from a set of known, previously solved, source tasks. In this paper, we argue that building stochastic abstract policies that generalize over past experiences is an effective way to provide such improvement and this generalization outperforms the current practice of using a library of policies. We achieve that contributing with a new algorithm, AbsProb-PI-multiple and a framework for transferring knowledge represented as a stochastic abstract policy in new RL tasks. Stochastic abstract policies offer an effective way to encode knowledge because the abstraction they provide not only generalizes solutions but also facilitates extracting the similarities among tasks. We perform experiments in a robotic navigation environment and analyze the agent's behavior throughout the learning process and also assess the transfer ratio for different amounts of source tasks. We compare our method with the transfer of a library of policies, and experiments show that the use of a generalized policy produces better results by more effectively guiding the agent when learning a target task.

Coupled replicator equations for the dynamics of learning in multiagent systems

NASA Astrophysics Data System (ADS)

Sato, Yuzuru; Crutchfield, James P.

2003-01-01

Starting with a group of reinforcement-learning agents we derive coupled replicator equations that describe the dynamics of collective learning in multiagent systems. We show that, although agents model their environment in a self-interested way without sharing knowledge, a game dynamics emerges naturally through environment-mediated interactions. An application to rock-scissors-paper game interactions shows that the collective learning dynamics exhibits a diversity of competitive and cooperative behaviors. These include quasiperiodicity, stable limit cycles, intermittency, and deterministic chaos—behaviors that should be expected in heterogeneous multiagent systems described by the general replicator equations we derive.

Reusable Reinforcement Learning via Shallow Trails.

PubMed

Yu, Yang; Chen, Shi-Yong; Da, Qing; Zhou, Zhi-Hua

2018-06-01

Reinforcement learning has shown great success in helping learning agents accomplish tasks autonomously from environment interactions. Meanwhile in many real-world applications, an agent needs to accomplish not only a fixed task but also a range of tasks. For this goal, an agent can learn a metapolicy over a set of training tasks that are drawn from an underlying distribution. By maximizing the total reward summed over all the training tasks, the metapolicy can then be reused in accomplishing test tasks from the same distribution. However, in practice, we face two major obstacles to train and reuse metapolicies well. First, how to identify tasks that are unrelated or even opposite with each other, in order to avoid their mutual interference in the training. Second, how to characterize task features, according to which a metapolicy can be reused. In this paper, we propose the MetA-Policy LEarning (MAPLE) approach that overcomes the two difficulties by introducing the shallow trail. It probes a task by running a roughly trained policy. Using the rewards of the shallow trail, MAPLE automatically groups similar tasks. Moreover, when the task parameters are unknown, the rewards of the shallow trail also serve as task features. Empirical studies on several controlling tasks verify that MAPLE can train metapolicies well and receives high reward on test tasks.

Decentralized learning in Markov games.

PubMed

Vrancx, Peter; Verbeeck, Katja; Nowé, Ann

2008-08-01

Learning automata (LA) were recently shown to be valuable tools for designing multiagent reinforcement learning algorithms. One of the principal contributions of the LA theory is that a set of decentralized independent LA is able to control a finite Markov chain with unknown transition probabilities and rewards. In this paper, we propose to extend this algorithm to Markov games--a straightforward extension of single-agent Markov decision problems to distributed multiagent decision problems. We show that under the same ergodic assumptions of the original theorem, the extended algorithm will converge to a pure equilibrium point between agent policies.

Online human training of a myoelectric prosthesis controller via actor-critic reinforcement learning.

PubMed

Pilarski, Patrick M; Dawson, Michael R; Degris, Thomas; Fahimi, Farbod; Carey, Jason P; Sutton, Richard S

2011-01-01

As a contribution toward the goal of adaptable, intelligent artificial limbs, this work introduces a continuous actor-critic reinforcement learning method for optimizing the control of multi-function myoelectric devices. Using a simulated upper-arm robotic prosthesis, we demonstrate how it is possible to derive successful limb controllers from myoelectric data using only a sparse human-delivered training signal, without requiring detailed knowledge about the task domain. This reinforcement-based machine learning framework is well suited for use by both patients and clinical staff, and may be easily adapted to different application domains and the needs of individual amputees. To our knowledge, this is the first my-oelectric control approach that facilitates the online learning of new amputee-specific motions based only on a one-dimensional (scalar) feedback signal provided by the user of the prosthesis. © 2011 IEEE

A computational neural model of goal-directed utterance selection.

PubMed

Klein, Michael; Kamp, Hans; Palm, Guenther; Doya, Kenji

2010-06-01

It is generally agreed that much of human communication is motivated by extra-linguistic goals: we often make utterances in order to get others to do something, or to make them support our cause, or adopt our point of view, etc. However, thus far a computational foundation for this view on language use has been lacking. In this paper we propose such a foundation using Markov Decision Processes. We borrow computational components from the field of action selection and motor control, where a neurobiological basis of these components has been established. In particular, we make use of internal models (i.e., next-state transition functions defined on current state action pairs). The internal model is coupled with reinforcement learning of a value function that is used to assess the desirability of any state that utterances (as well as certain non-verbal actions) can bring about. This cognitive architecture is tested in a number of multi-agent game simulations. In these computational experiments an agent learns to predict the context-dependent effects of utterances by interacting with other agents that are already competent speakers. We show that the cognitive architecture can account for acquiring the capability of deciding when to speak in order to achieve a certain goal (instead of performing a non-verbal action or simply doing nothing), whom to address and what to say. Copyright 2010 Elsevier Ltd. All rights reserved.

Reinforcement learning in professional basketball players

PubMed Central

Neiman, Tal; Loewenstein, Yonatan

2011-01-01

Reinforcement learning in complex natural environments is a challenging task because the agent should generalize from the outcomes of actions taken in one state of the world to future actions in different states of the world. The extent to which human experts find the proper level of generalization is unclear. Here we show, using the sequences of field goal attempts made by professional basketball players, that the outcome of even a single field goal attempt has a considerable effect on the rate of subsequent 3 point shot attempts, in line with standard models of reinforcement learning. However, this change in behaviour is associated with negative correlations between the outcomes of successive field goal attempts. These results indicate that despite years of experience and high motivation, professional players overgeneralize from the outcomes of their most recent actions, which leads to decreased performance. PMID:22146388

Cooperative learning neural network output feedback control of uncertain nonlinear multi-agent systems under directed topologies

NASA Astrophysics Data System (ADS)

Wang, W.; Wang, D.; Peng, Z. H.

2017-09-01

Without assuming that the communication topologies among the neural network (NN) weights are to be undirected and the states of each agent are measurable, the cooperative learning NN output feedback control is addressed for uncertain nonlinear multi-agent systems with identical structures in strict-feedback form. By establishing directed communication topologies among NN weights to share their learned knowledge, NNs with cooperative learning laws are employed to identify the uncertainties. By designing NN-based κ-filter observers to estimate the unmeasurable states, a new cooperative learning output feedback control scheme is proposed to guarantee that the system outputs can track nonidentical reference signals with bounded tracking errors. A simulation example is given to demonstrate the effectiveness of the theoretical results.

The evolution of continuous learning of the structure of the environment

PubMed Central

Kolodny, Oren; Edelman, Shimon; Lotem, Arnon

2014-01-01

Continuous, ‘always on’, learning of structure from a stream of data is studied mainly in the fields of machine learning or language acquisition, but its evolutionary roots may go back to the first organisms that were internally motivated to learn and represent their environment. Here, we study under what conditions such continuous learning (CL) may be more adaptive than simple reinforcement learning and examine how it could have evolved from the same basic associative elements. We use agent-based computer simulations to compare three learning strategies: simple reinforcement learning; reinforcement learning with chaining (RL-chain) and CL that applies the same associative mechanisms used by the other strategies, but also seeks statistical regularities in the relations among all items in the environment, regardless of the initial association with food. We show that a sufficiently structured environment favours the evolution of both RL-chain and CL and that CL outperforms the other strategies when food is relatively rare and the time for learning is limited. This advantage of internally motivated CL stems from its ability to capture statistical patterns in the environment even before they are associated with food, at which point they immediately become useful for planning. PMID:24402920

Learning from Multiple Collaborating Intelligent Tutors: An Agent-based Approach.

ERIC Educational Resources Information Center

Solomos, Konstantinos; Avouris, Nikolaos

1999-01-01

Describes an open distributed multi-agent tutoring system (MATS) and discusses issues related to learning in such open environments. Topics include modeling a one student-many teachers approach in a computer-based learning context; distributed artificial intelligence; implementation issues; collaboration; and user interaction. (Author/LRW)

Dopaminergic Balance between Reward Maximization and Policy Complexity

PubMed Central

Parush, Naama; Tishby, Naftali; Bergman, Hagai

2011-01-01

Previous reinforcement-learning models of the basal ganglia network have highlighted the role of dopamine in encoding the mismatch between prediction and reality. Far less attention has been paid to the computational goals and algorithms of the main-axis (actor). Here, we construct a top-down model of the basal ganglia with emphasis on the role of dopamine as both a reinforcement learning signal and as a pseudo-temperature signal controlling the general level of basal ganglia excitability and motor vigilance of the acting agent. We argue that the basal ganglia endow the thalamic-cortical networks with the optimal dynamic tradeoff between two constraints: minimizing the policy complexity (cost) and maximizing the expected future reward (gain). We show that this multi-dimensional optimization processes results in an experience-modulated version of the softmax behavioral policy. Thus, as in classical softmax behavioral policies, probability of actions are selected according to their estimated values and the pseudo-temperature, but in addition also vary according to the frequency of previous choices of these actions. We conclude that the computational goal of the basal ganglia is not to maximize cumulative (positive and negative) reward. Rather, the basal ganglia aim at optimization of independent gain and cost functions. Unlike previously suggested single-variable maximization processes, this multi-dimensional optimization process leads naturally to a softmax-like behavioral policy. We suggest that beyond its role in the modulation of the efficacy of the cortico-striatal synapses, dopamine directly affects striatal excitability and thus provides a pseudo-temperature signal that modulates the tradeoff between gain and cost. The resulting experience and dopamine modulated softmax policy can then serve as a theoretical framework to account for the broad range of behaviors and clinical states governed by the basal ganglia and dopamine systems. PMID:21603228

Proposed Methodology for Application of Human-like gradual Multi-Agent Q-Learning (HuMAQ) for Multi-robot Exploration

NASA Astrophysics Data System (ADS)

Narayan Ray, Dip; Majumder, Somajyoti

2014-07-01

Several attempts have been made by the researchers around the world to develop a number of autonomous exploration techniques for robots. But it has been always an important issue for developing the algorithm for unstructured and unknown environments. Human-like gradual Multi-agent Q-leaming (HuMAQ) is a technique developed for autonomous robotic exploration in unknown (and even unimaginable) environments. It has been successfully implemented in multi-agent single robotic system. HuMAQ uses the concept of Subsumption architecture, a well-known Behaviour-based architecture for prioritizing the agents of the multi-agent system and executes only the most common action out of all the different actions recommended by different agents. Instead of using new state-action table (Q-table) each time, HuMAQ uses the immediate past table for efficient and faster exploration. The proof of learning has also been established both theoretically and practically. HuMAQ has the potential to be used in different and difficult situations as well as applications. The same architecture has been modified to use for multi-robot exploration in an environment. Apart from all other existing agents used in the single robotic system, agents for inter-robot communication and coordination/ co-operation with the other similar robots have been introduced in the present research. Current work uses a series of indigenously developed identical autonomous robotic systems, communicating with each other through ZigBee protocol.

Quantum machine learning with glow for episodic tasks and decision games

NASA Astrophysics Data System (ADS)

Clausen, Jens; Briegel, Hans J.

2018-02-01

We consider a general class of models, where a reinforcement learning (RL) agent learns from cyclic interactions with an external environment via classical signals. Perceptual inputs are encoded as quantum states, which are subsequently transformed by a quantum channel representing the agent's memory, while the outcomes of measurements performed at the channel's output determine the agent's actions. The learning takes place via stepwise modifications of the channel properties. They are described by an update rule that is inspired by the projective simulation (PS) model and equipped with a glow mechanism that allows for a backpropagation of policy changes, analogous to the eligibility traces in RL and edge glow in PS. In this way, the model combines features of PS with the ability for generalization, offered by its physical embodiment as a quantum system. We apply the agent to various setups of an invasion game and a grid world, which serve as elementary model tasks allowing a direct comparison with a basic classical PS agent.

Modeling Peer Assessment as Agent Negotiation in a Computer Supported Collaborative Learning Environment

ERIC Educational Resources Information Center

Lai, K. Robert; Lan, Chung Hsien

2006-01-01

This work presents a novel method for modeling collaborative learning as multi-issue agent negotiation using fuzzy constraints. Agent negotiation is an iterative process, through which, the proposed method aggregates student marks to reduce personal bias. In the framework, students define individual fuzzy membership functions based on their…

Clipping in neurocontrol by adaptive dynamic programming.

PubMed

Fairbank, Michael; Prokhorov, Danil; Alonso, Eduardo

2014-10-01

In adaptive dynamic programming, neurocontrol, and reinforcement learning, the objective is for an agent to learn to choose actions so as to minimize a total cost function. In this paper, we show that when discretized time is used to model the motion of the agent, it can be very important to do clipping on the motion of the agent in the final time step of the trajectory. By clipping, we mean that the final time step of the trajectory is to be truncated such that the agent stops exactly at the first terminal state reached, and no distance further. We demonstrate that when clipping is omitted, learning performance can fail to reach the optimum, and when clipping is done properly, learning performance can improve significantly. The clipping problem we describe affects algorithms that use explicit derivatives of the model functions of the environment to calculate a learning gradient. These include backpropagation through time for control and methods based on dual heuristic programming. However, the clipping problem does not significantly affect methods based on heuristic dynamic programming, temporal differences learning, or policy-gradient learning algorithms.

Use of Frontal Lobe Hemodynamics as Reinforcement Signals to an Adaptive Controller

PubMed Central

DiStasio, Marcello M.; Francis, Joseph T.

2013-01-01

Decision-making ability in the frontal lobe (among other brain structures) relies on the assignment of value to states of the animal and its environment. Then higher valued states can be pursued and lower (or negative) valued states avoided. The same principle forms the basis for computational reinforcement learning controllers, which have been fruitfully applied both as models of value estimation in the brain, and as artificial controllers in their own right. This work shows how state desirability signals decoded from frontal lobe hemodynamics, as measured with near-infrared spectroscopy (NIRS), can be applied as reinforcers to an adaptable artificial learning agent in order to guide its acquisition of skills. A set of experiments carried out on an alert macaque demonstrate that both oxy- and deoxyhemoglobin concentrations in the frontal lobe show differences in response to both primarily and secondarily desirable (versus undesirable) stimuli. This difference allows a NIRS signal classifier to serve successfully as a reinforcer for an adaptive controller performing a virtual tool-retrieval task. The agent's adaptability allows its performance to exceed the limits of the NIRS classifier decoding accuracy. We also show that decoding state desirabilities is more accurate when using relative concentrations of both oxyhemoglobin and deoxyhemoglobin, rather than either species alone. PMID:23894500

Research and application of multi-agent genetic algorithm in tower defense game

NASA Astrophysics Data System (ADS)

Jin, Shaohua

2018-04-01

In this paper, a new multi-agent genetic algorithm based on orthogonal experiment is proposed, which is based on multi-agent system, genetic algorithm and orthogonal experimental design. The design of neighborhood competition operator, orthogonal crossover operator, Son and self-learning operator. The new algorithm is applied to mobile tower defense game, according to the characteristics of the game, the establishment of mathematical models, and finally increases the value of the game's monster.

Risk-aware multi-armed bandit problem with application to portfolio selection

PubMed Central

Huo, Xiaoguang

2017-01-01

Sequential portfolio selection has attracted increasing interest in the machine learning and quantitative finance communities in recent years. As a mathematical framework for reinforcement learning policies, the stochastic multi-armed bandit problem addresses the primary difficulty in sequential decision-making under uncertainty, namely the exploration versus exploitation dilemma, and therefore provides a natural connection to portfolio selection. In this paper, we incorporate risk awareness into the classic multi-armed bandit setting and introduce an algorithm to construct portfolio. Through filtering assets based on the topological structure of the financial market and combining the optimal multi-armed bandit policy with the minimization of a coherent risk measure, we achieve a balance between risk and return. PMID:29291122

Risk-aware multi-armed bandit problem with application to portfolio selection.

PubMed

Huo, Xiaoguang; Fu, Feng

2017-11-01

Sequential portfolio selection has attracted increasing interest in the machine learning and quantitative finance communities in recent years. As a mathematical framework for reinforcement learning policies, the stochastic multi-armed bandit problem addresses the primary difficulty in sequential decision-making under uncertainty, namely the exploration versus exploitation dilemma, and therefore provides a natural connection to portfolio selection. In this paper, we incorporate risk awareness into the classic multi-armed bandit setting and introduce an algorithm to construct portfolio. Through filtering assets based on the topological structure of the financial market and combining the optimal multi-armed bandit policy with the minimization of a coherent risk measure, we achieve a balance between risk and return.

Intrinsically motivated reinforcement learning for human-robot interaction in the real-world.

PubMed

Qureshi, Ahmed Hussain; Nakamura, Yutaka; Yoshikawa, Yuichiro; Ishiguro, Hiroshi

2018-03-26

For a natural social human-robot interaction, it is essential for a robot to learn the human-like social skills. However, learning such skills is notoriously hard due to the limited availability of direct instructions from people to teach a robot. In this paper, we propose an intrinsically motivated reinforcement learning framework in which an agent gets the intrinsic motivation-based rewards through the action-conditional predictive model. By using the proposed method, the robot learned the social skills from the human-robot interaction experiences gathered in the real uncontrolled environments. The results indicate that the robot not only acquired human-like social skills but also took more human-like decisions, on a test dataset, than a robot which received direct rewards for the task achievement. Copyright © 2018 Elsevier Ltd. All rights reserved.

A New Consequence of Simpson's Paradox: Stable Cooperation in One-Shot Prisoner's Dilemma from Populations of Individualistic Learners

ERIC Educational Resources Information Center

Chater, Nick; Vlaev, Ivo; Grinberg, Maurice

2008-01-01

Theories of choice in economics typically assume that interacting agents act individualistically and maximize their own utility. Specifically, game theory proposes that rational players should defect in one-shot prisoners' dilemmas (PD). Defection also appears to be the inevitable outcome for agents who learn by reinforcement of past choices,…

Neural Modularity Helps Organisms Evolve to Learn New Skills without Forgetting Old Skills

PubMed Central

Ellefsen, Kai Olav; Mouret, Jean-Baptiste; Clune, Jeff

2015-01-01

A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new skill they typically do so by losing previously acquired skills, a problem called catastrophic forgetting. That occurs because, to learn the new task, neural learning algorithms change connections that encode previously acquired skills. How networks are organized critically affects their learning dynamics. In this paper, we test whether catastrophic forgetting can be reduced by evolving modular neural networks. Modularity intuitively should reduce learning interference between tasks by separating functionality into physically distinct modules in which learning can be selectively turned on or off. Modularity can further improve learning by having a reinforcement learning module separate from sensory processing modules, allowing learning to happen only in response to a positive or negative reward. In this paper, learning takes place via neuromodulation, which allows agents to selectively change the rate of learning for each neural connection based on environmental stimuli (e.g. to alter learning in specific locations based on the task at hand). To produce modularity, we evolve neural networks with a cost for neural connections. We show that this connection cost technique causes modularity, confirming a previous result, and that such sparsely connected, modular networks have higher overall performance because they learn new skills faster while retaining old skills more and because they have a separate reinforcement learning module. Our results suggest (1) that encouraging modularity in neural networks may help us overcome the long-standing barrier of networks that cannot learn new skills without forgetting old ones, and (2) that one benefit of the modularity ubiquitous in the brains of natural animals might be to alleviate the problem of catastrophic forgetting. PMID:25837826

Neural modularity helps organisms evolve to learn new skills without forgetting old skills.

PubMed

Ellefsen, Kai Olav; Mouret, Jean-Baptiste; Clune, Jeff

2015-04-01

A long-standing goal in artificial intelligence is creating agents that can learn a variety of different skills for different problems. In the artificial intelligence subfield of neural networks, a barrier to that goal is that when agents learn a new skill they typically do so by losing previously acquired skills, a problem called catastrophic forgetting. That occurs because, to learn the new task, neural learning algorithms change connections that encode previously acquired skills. How networks are organized critically affects their learning dynamics. In this paper, we test whether catastrophic forgetting can be reduced by evolving modular neural networks. Modularity intuitively should reduce learning interference between tasks by separating functionality into physically distinct modules in which learning can be selectively turned on or off. Modularity can further improve learning by having a reinforcement learning module separate from sensory processing modules, allowing learning to happen only in response to a positive or negative reward. In this paper, learning takes place via neuromodulation, which allows agents to selectively change the rate of learning for each neural connection based on environmental stimuli (e.g. to alter learning in specific locations based on the task at hand). To produce modularity, we evolve neural networks with a cost for neural connections. We show that this connection cost technique causes modularity, confirming a previous result, and that such sparsely connected, modular networks have higher overall performance because they learn new skills faster while retaining old skills more and because they have a separate reinforcement learning module. Our results suggest (1) that encouraging modularity in neural networks may help us overcome the long-standing barrier of networks that cannot learn new skills without forgetting old ones, and (2) that one benefit of the modularity ubiquitous in the brains of natural animals might be to alleviate the problem of catastrophic forgetting.

Two-Dimensional Nanostructure- Reinforced Biodegradable Polymeric Nanocomposites for Bone Tissue Engineering

PubMed Central

Lalwani, Gaurav; Henslee, Allan M.; Farshid, Behzad; Lin, Liangjun; Kasper, F. Kurtis; Qin, Yi-Xian; Mikos, Antonios G.; Sitharaman, Balaji

2013-01-01

This study investigates the efficacy of two dimensional (2D) carbon and inorganic nanostructures as reinforcing agents of crosslinked composites of the biodegradable and biocompatible polymer polypropylene fumarate (PPF) as a function of nanostructure concentration. PPF composites were reinforced using various 2D nanostructures: single- and multi-walled graphene oxide nanoribbons (SWGONRs, MWGONRs), graphene oxide nanoplatelets (GONPs), and molybdenum di-sulfite nanoplatelets (MSNPs) at 0.01–0.2 weight% concentrations. Cross-linked PPF was used as the baseline control, and PPF composites reinforced with single- or multi-walled carbon nanotubes (SWCNT, MWCNT) were used as positive controls. Compression and flexural testing show a significant enhancement (i.e., compressive modulus = 35–108%, compressive yield strength = 26–93%, flexural modulus = 15–53%, and flexural yield strength = 101–262% greater than the baseline control) in the mechanical properties of the 2D-reinforced PPF nanocomposites. MSNPs nanocomposites consistently showed the highest values among the experimental or control groups in all the mechanical measurements. In general, the inorganic nanoparticle MSNPs showed a better or equivalent mechanical reinforcement compared to carbon nanomaterials, and 2-D nanostructures (GONP, MSNP) are better reinforcing agents compared to 1-D nanostructures (e.g. SWCNTs). The results also indicate that the extent of mechanical reinforcement is closely dependent on the nanostructure morphology and follows the trend nanoplatelets > nanoribbons > nanotubes. Transmission electron microscopy of the cross-linked nanocomposites indicates good dispersion of nanomaterials in the polymer matrix without the use of a surfactant. The sol-fraction analysis showed significant changes in the polymer cross-linking in the presence of MSNP (0.01–0.2 wt %) and higher loading concentrations of GONP and MWGONR (0.1–0.2 wt%). The analysis of surface area and aspect ratio of the nanostructures taken together with the above results indicates differences in nanostructure architecture (2D vs. 1D nanostructures), as well as the chemical compositions (inorganic vs. carbon nanostructures), number of functional groups, and structural defects for the 2D nanostructures maybe key properties that affect the mechanical properties of 2D nanostructure-reinforced PPF nanocomposites, and the reason for the enhanced mechanical properties compared to the controls. PMID:23405887

A new consequence of Simpson's paradox: stable cooperation in one-shot prisoner's dilemma from populations of individualistic learners.

PubMed

Chater, Nick; Vlaev, Ivo; Grinberg, Maurice

2008-08-01

Theories of choice in economics typically assume that interacting agents act individualistically and maximize their own utility. Specifically, game theory proposes that rational players should defect in one-shot prisoners' dilemmas (PD). Defection also appears to be the inevitable outcome for agents who learn by reinforcement of past choices, because whatever the other player does, defection leads to greater reinforcement on each trial. In a computer simulation and 4 experiments, the authors show that, apparently paradoxically, when players' choices are correlated by an exogenous factor (here, the cooperativeness of the specific PD chosen), people obtain greater average reinforcement for cooperating, which can sustain cooperation. This effect arises from a well-known statistical paradox, Simpson's paradox. The authors speculate that this effect may be relevant to aspects of real-world human cooperative behavior.

Accelerating Multiagent Reinforcement Learning by Equilibrium Transfer.

PubMed

Hu, Yujing; Gao, Yang; An, Bo

2015-07-01

An important approach in multiagent reinforcement learning (MARL) is equilibrium-based MARL, which adopts equilibrium solution concepts in game theory and requires agents to play equilibrium strategies at each state. However, most existing equilibrium-based MARL algorithms cannot scale due to a large number of computationally expensive equilibrium computations (e.g., computing Nash equilibria is PPAD-hard) during learning. For the first time, this paper finds that during the learning process of equilibrium-based MARL, the one-shot games corresponding to each state's successive visits often have the same or similar equilibria (for some states more than 90% of games corresponding to successive visits have similar equilibria). Inspired by this observation, this paper proposes to use equilibrium transfer to accelerate equilibrium-based MARL. The key idea of equilibrium transfer is to reuse previously computed equilibria when each agent has a small incentive to deviate. By introducing transfer loss and transfer condition, a novel framework called equilibrium transfer-based MARL is proposed. We prove that although equilibrium transfer brings transfer loss, equilibrium-based MARL algorithms can still converge to an equilibrium policy under certain assumptions. Experimental results in widely used benchmarks (e.g., grid world game, soccer game, and wall game) show that the proposed framework: 1) not only significantly accelerates equilibrium-based MARL (up to 96.7% reduction in learning time), but also achieves higher average rewards than algorithms without equilibrium transfer and 2) scales significantly better than algorithms without equilibrium transfer when the state/action space grows and the number of agents increases.

An interactive online robotics course.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Wedeward, Kevin; Bruder, Steven B. H.

Attempting to convey concepts and ideas in the subject area of robotic manipulators from within the confines of a static two-dimensional printed page can prove quite challenging to even the most gifted of authors. The inherently dynamic and multi-dimensional nature of the subject matter seems better suited to a medium of conveyance wherein a student is allowed to interactively explore topics in this multi-disciplinary field. This article describes the initial development of an online robotics course 'textbook' which seeks to leverage recent advances in Web-based technologies to enhance the learning experience in ways not possible with printed materials. The pedagogicalmore » approach employed herein is that of multi-modal reinforcement wherein key concepts are first described in words, conveyed visually, and finally reinforced by soliciting student interaction.« less

Multi-objective optimization of radiotherapy: distributed Q-learning and agent-based simulation

NASA Astrophysics Data System (ADS)

Jalalimanesh, Ammar; Haghighi, Hamidreza Shahabi; Ahmadi, Abbas; Hejazian, Hossein; Soltani, Madjid

2017-09-01

Radiotherapy (RT) is among the regular techniques for the treatment of cancerous tumours. Many of cancer patients are treated by this manner. Treatment planning is the most important phase in RT and it plays a key role in therapy quality achievement. As the goal of RT is to irradiate the tumour with adequately high levels of radiation while sparing neighbouring healthy tissues as much as possible, it is a multi-objective problem naturally. In this study, we propose an agent-based model of vascular tumour growth and also effects of RT. Next, we use multi-objective distributed Q-learning algorithm to find Pareto-optimal solutions for calculating RT dynamic dose. We consider multiple objectives and each group of optimizer agents attempt to optimise one of them, iteratively. At the end of each iteration, agents compromise the solutions to shape the Pareto-front of multi-objective problem. We propose a new approach by defining three schemes of treatment planning created based on different combinations of our objectives namely invasive, conservative and moderate. In invasive scheme, we enforce killing cancer cells and pay less attention about irradiation effects on normal cells. In conservative scheme, we take more care of normal cells and try to destroy cancer cells in a less stressed manner. The moderate scheme stands in between. For implementation, each of these schemes is handled by one agent in MDQ-learning algorithm and the Pareto optimal solutions are discovered by the collaboration of agents. By applying this methodology, we could reach Pareto treatment plans through building different scenarios of tumour growth and RT. The proposed multi-objective optimisation algorithm generates robust solutions and finds the best treatment plan for different conditions.

A framework for learning and planning against switching strategies in repeated games

NASA Astrophysics Data System (ADS)

Hernandez-Leal, Pablo; Munoz de Cote, Enrique; Sucar, L. Enrique

2014-04-01

Intelligent agents, human or artificial, often change their behaviour as they interact with other agents. For an agent to optimise its performance when interacting with such agents, it must be capable of detecting and adapting according to such changes. This work presents an approach on how to effectively deal with non-stationary switching opponents in a repeated game context. Our main contribution is a framework for online learning and planning against opponents that switch strategies. We present how two opponent modelling techniques work within the framework and prove the usefulness of the approach experimentally in the iterated prisoner's dilemma, when the opponent is modelled as an agent that switches between different strategies (e.g. TFT, Pavlov and Bully). The results of both models were compared against each other and against a state-of-the-art non-stationary reinforcement learning technique. Results reflect that our approach obtains competitive results without needing an offline training phase, as opposed to the state-of-the-art techniques.

Multi-Objective Reinforcement Learning-based Deep Neural Networks for Cognitive Space Communications

NASA Technical Reports Server (NTRS)

Ferreria, Paulo; Paffenroth, Randy; Wyglinski, Alexander M.; Hackett, Timothy; Bilen, Sven; Reinhart, Richard; Mortensen, Dale

2017-01-01

Future communication subsystems of space exploration missions can potentially benefit from software-defined radios (SDRs) controlled by machine learning algorithms. In this paper, we propose a novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement learning and deep artificial neural networks. The objective is to efficiently manage communications system resources by monitoring performance functions with common dependent variables that result in conflicting goals. The uncertainty in the performance of thousands of different possible combinations of radio parameters makes the trade-off between exploration and exploitation in reinforcement learning (RL) much more challenging for future critical space-based missions. Thus, the system should spend as little time as possible on exploring actions, and whenever it explores an action, it should perform at acceptable levels most of the time. The proposed approach enables on-line learning by interactions with the environment and restricts poor resource allocation performance through virtual environment exploration. Improvements in the multiobjective performance can be achieved via transmitter parameter adaptation on a packet-basis, with poorly predicted performance promptly resulting in rejected decisions. Simulations presented in this work considered the DVB-S2 standard adaptive transmitter parameters and additional ones expected to be present in future adaptive radio systems. Performance results are provided by analysis of the proposed hybrid algorithm when operating across a satellite communication channel from Earth to GEO orbit during clear sky conditions. The proposed approach constitutes part of the core cognitive engine proof-of-concept to be delivered to the NASA Glenn Research Center SCaN Testbed located onboard the International Space Station.

Multi-Objective Reinforcement Learning-Based Deep Neural Networks for Cognitive Space Communications

NASA Technical Reports Server (NTRS)

Ferreria, Paulo Victor R.; Paffenroth, Randy; Wyglinski, Alexander M.; Hackett, Timothy M.; Bilen, Sven G.; Reinhart, Richard C.; Mortensen, Dale J.

2017-01-01

Future communication subsystems of space exploration missions can potentially benefit from software-defined radios (SDRs) controlled by machine learning algorithms. In this paper, we propose a novel hybrid radio resource allocation management control algorithm that integrates multi-objective reinforcement learning and deep artificial neural networks. The objective is to efficiently manage communications system resources by monitoring performance functions with common dependent variables that result in conflicting goals. The uncertainty in the performance of thousands of different possible combinations of radio parameters makes the trade-off between exploration and exploitation in reinforcement learning (RL) much more challenging for future critical space-based missions. Thus, the system should spend as little time as possible on exploring actions, and whenever it explores an action, it should perform at acceptable levels most of the time. The proposed approach enables on-line learning by interactions with the environment and restricts poor resource allocation performance through virtual environment exploration. Improvements in the multiobjective performance can be achieved via transmitter parameter adaptation on a packet-basis, with poorly predicted performance promptly resulting in rejected decisions. Simulations presented in this work considered the DVB-S2 standard adaptive transmitter parameters and additional ones expected to be present in future adaptive radio systems. Performance results are provided by analysis of the proposed hybrid algorithm when operating across a satellite communication channel from Earth to GEO orbit during clear sky conditions. The proposed approach constitutes part of the core cognitive engine proof-of-concept to be delivered to the NASA Glenn Research Center SCaN Testbed located onboard the International Space Station.

Exact solution of a modified El Farol's bar problem: Efficiency and the role of market impact

NASA Astrophysics Data System (ADS)

Marsili, Matteo; Challet, Damien; Zecchina, Riccardo

2000-06-01

We discuss a model of heterogeneous, inductive rational agents inspired by the El Farol Bar problem and the Minority Game. As in markets, agents interact through a collective aggregate variable - which plays a role similar to price - whose value is fixed by all of them. Agents follow a simple reinforcement-learning dynamics where the reinforcement, for each of their available strategies, is related to the payoff delivered by that strategy. We derive the exact solution of the model in the “thermodynamic” limit of infinitely many agents using tools of statistical physics of disordered systems. Our results show that the impact of agents on the market price plays a key role: even though price has a weak dependence on the behavior of each individual agent, the collective behavior crucially depends on whether agents account for such dependence or not. Remarkably, if the adaptive behavior of agents accounts even “infinitesimally” for this dependence they can, in a whole range of parameters, reduce global fluctuations by a finite amount. Both global efficiency and individual utility improve with respect to a “price taker” behavior if agents account for their market impact.

Reinforcement Learning with Autonomous Small Unmanned Aerial Vehicles in Cluttered Environments

NASA Technical Reports Server (NTRS)

Tran, Loc; Cross, Charles; Montague, Gilbert; Motter, Mark; Neilan, James; Qualls, Garry; Rothhaar, Paul; Trujillo, Anna; Allen, B. Danette

2015-01-01

We present ongoing work in the Autonomy Incubator at NASA Langley Research Center (LaRC) exploring the efficacy of a data set aggregation approach to reinforcement learning for small unmanned aerial vehicle (sUAV) flight in dense and cluttered environments with reactive obstacle avoidance. The goal is to learn an autonomous flight model using training experiences from a human piloting a sUAV around static obstacles. The training approach uses video data from a forward-facing camera that records the human pilot's flight. Various computer vision based features are extracted from the video relating to edge and gradient information. The recorded human-controlled inputs are used to train an autonomous control model that correlates the extracted feature vector to a yaw command. As part of the reinforcement learning approach, the autonomous control model is iteratively updated with feedback from a human agent who corrects undesired model output. This data driven approach to autonomous obstacle avoidance is explored for simulated forest environments furthering autonomous flight under the tree canopy research. This enables flight in previously inaccessible environments which are of interest to NASA researchers in Earth and Atmospheric sciences.

Strengthening behavior of chopped multi-walled carbon nanotube reinforced aluminum matrix composites

DOE Office of Scientific and Technical Information (OSTI.GOV)

Shin, S.E.; Bae, D.H., E-mail: donghyun@yonsei.ac.kr

2013-09-15

Strengthening behavior of the aluminum composites reinforced with chopped multi-walled carbon nanotubes (MWCNTs) or aluminum carbide formed during annealing at 500 °C has been investigated. The composites were fabricated by hot-rolling the powders which were ball-milled under various conditions. During the early annealing process, aluminum atoms can cluster inside the tube due to the diffusional flow of aluminum atoms into the tube, providing an increase of the strength of the composite. Further annealing induces the formation of the aluminum carbide phase, leading to an overall drop in the strength of the composites. While the strength of the composites can bemore » evaluated according to the rule of mixture, a particle spacing effect can be additionally imparted on the strength of the composites reinforced with the chopped MWCNTs or the corresponding carbides since the reinforcing agents are smaller than the submicron matrix grains. - Highlights: • Strengthening behavior of chopped CNT reinforced Al-based composites is investigated. • Chopped CNTs have influenced the strength and microstructures of the composites. • Chopped CNTs are created under Ar- 3% H2 atmosphere during mechanical milling. • Strength can be evaluated by the rule of the mixture and a particle spacing effect.« less

A Multi-Agent System Approach for Distance Learning Architecture

ERIC Educational Resources Information Center

Turgay, Safiye

2005-01-01

The goal of this study is to suggest the agent systems by intelligence and adaptability properties in distance learning environment. The suggested system has flexible, agile, intelligence and cooperation features. System components are teachers, students (learners), and resources. Inter component relations are modeled and reviewed by using the…

Argumentation Based Joint Learning: A Novel Ensemble Learning Approach

PubMed Central

Xu, Junyi; Yao, Li; Li, Le

2015-01-01

Recently, ensemble learning methods have been widely used to improve classification performance in machine learning. In this paper, we present a novel ensemble learning method: argumentation based multi-agent joint learning (AMAJL), which integrates ideas from multi-agent argumentation, ensemble learning, and association rule mining. In AMAJL, argumentation technology is introduced as an ensemble strategy to integrate multiple base classifiers and generate a high performance ensemble classifier. We design an argumentation framework named Arena as a communication platform for knowledge integration. Through argumentation based joint learning, high quality individual knowledge can be extracted, and thus a refined global knowledge base can be generated and used independently for classification. We perform numerous experiments on multiple public datasets using AMAJL and other benchmark methods. The results demonstrate that our method can effectively extract high quality knowledge for ensemble classifier and improve the performance of classification. PMID:25966359

Discrete-time online learning control for a class of unknown nonaffine nonlinear systems using reinforcement learning.

PubMed

Yang, Xiong; Liu, Derong; Wang, Ding; Wei, Qinglai

2014-07-01

In this paper, a reinforcement-learning-based direct adaptive control is developed to deliver a desired tracking performance for a class of discrete-time (DT) nonlinear systems with unknown bounded disturbances. We investigate multi-input-multi-output unknown nonaffine nonlinear DT systems and employ two neural networks (NNs). By using Implicit Function Theorem, an action NN is used to generate the control signal and it is also designed to cancel the nonlinearity of unknown DT systems, for purpose of utilizing feedback linearization methods. On the other hand, a critic NN is applied to estimate the cost function, which satisfies the recursive equations derived from heuristic dynamic programming. The weights of both the action NN and the critic NN are directly updated online instead of offline training. By utilizing Lyapunov's direct method, the closed-loop tracking errors and the NN estimated weights are demonstrated to be uniformly ultimately bounded. Two numerical examples are provided to show the effectiveness of the present approach. Copyright © 2014 Elsevier Ltd. All rights reserved.

Projective simulation for artificial intelligence

NASA Astrophysics Data System (ADS)

Briegel, Hans J.; de Las Cuevas, Gemma

2012-05-01

We propose a model of a learning agent whose interaction with the environment is governed by a simulation-based projection, which allows the agent to project itself into future situations before it takes real action. Projective simulation is based on a random walk through a network of clips, which are elementary patches of episodic memory. The network of clips changes dynamically, both due to new perceptual input and due to certain compositional principles of the simulation process. During simulation, the clips are screened for specific features which trigger factual action of the agent. The scheme is different from other, computational, notions of simulation, and it provides a new element in an embodied cognitive science approach to intelligent action and learning. Our model provides a natural route for generalization to quantum-mechanical operation and connects the fields of reinforcement learning and quantum computation.

Projective simulation for artificial intelligence

PubMed Central

Briegel, Hans J.; De las Cuevas, Gemma

2012-01-01

We propose a model of a learning agent whose interaction with the environment is governed by a simulation-based projection, which allows the agent to project itself into future situations before it takes real action. Projective simulation is based on a random walk through a network of clips, which are elementary patches of episodic memory. The network of clips changes dynamically, both due to new perceptual input and due to certain compositional principles of the simulation process. During simulation, the clips are screened for specific features which trigger factual action of the agent. The scheme is different from other, computational, notions of simulation, and it provides a new element in an embodied cognitive science approach to intelligent action and learning. Our model provides a natural route for generalization to quantum-mechanical operation and connects the fields of reinforcement learning and quantum computation. PMID:22590690

Leader-Follower Output Synchronization of Linear Heterogeneous Systems With Active Leader Using Reinforcement Learning.

PubMed

Yang, Yongliang; Modares, Hamidreza; Wunsch, Donald C; Yin, Yixin

2018-06-01

This paper develops optimal control protocols for the distributed output synchronization problem of leader-follower multiagent systems with an active leader. Agents are assumed to be heterogeneous with different dynamics and dimensions. The desired trajectory is assumed to be preplanned and is generated by the leader. Other follower agents autonomously synchronize to the leader by interacting with each other using a communication network. The leader is assumed to be active in the sense that it has a nonzero control input so that it can act independently and update its control to keep the followers away from possible danger. A distributed observer is first designed to estimate the leader's state and generate the reference signal for each follower. Then, the output synchronization of leader-follower systems with an active leader is formulated as a distributed optimal tracking problem, and inhomogeneous algebraic Riccati equations (AREs) are derived to solve it. The resulting distributed optimal control protocols not only minimize the steady-state error but also optimize the transient response of the agents. An off-policy reinforcement learning algorithm is developed to solve the inhomogeneous AREs online in real time and without requiring any knowledge of the agents' dynamics. Finally, two simulation examples are conducted to illustrate the effectiveness of the proposed algorithm.

A Novel Clustering Method Curbing the Number of States in Reinforcement Learning

NASA Astrophysics Data System (ADS)

Kotani, Naoki; Nunobiki, Masayuki; Taniguchi, Kenji

We propose an efficient state-space construction method for a reinforcement learning. Our method controls the number of categories with improving the clustering method of Fuzzy ART which is an autonomous state-space construction method. The proposed method represents weight vector as the mean value of input vectors in order to curb the number of new categories and eliminates categories whose state values are low to curb the total number of categories. As the state value is updated, the size of category becomes small to learn policy strictly. We verified the effectiveness of the proposed method with simulations of a reaching problem for a two-link robot arm. We confirmed that the number of categories was reduced and the agent achieved the complex task quickly.

Learning to make collective decisions: the impact of confidence escalation.

PubMed

Mahmoodi, Ali; Bang, Dan; Ahmadabadi, Majid Nili; Bahrami, Bahador

2013-01-01

Little is known about how people learn to take into account others' opinions in joint decisions. To address this question, we combined computational and empirical approaches. Human dyads made individual and joint visual perceptual decision and rated their confidence in those decisions (data previously published). We trained a reinforcement (temporal difference) learning agent to get the participants' confidence level and learn to arrive at a dyadic decision by finding the policy that either maximized the accuracy of the model decisions or maximally conformed to the empirical dyadic decisions. When confidences were shared visually without verbal interaction, RL agents successfully captured social learning. When participants exchanged confidences visually and interacted verbally, no collective benefit was achieved and the model failed to predict the dyadic behaviour. Behaviourally, dyad members' confidence increased progressively and verbal interaction accelerated this escalation. The success of the model in drawing collective benefit from dyad members was inversely related to confidence escalation rate. The findings show an automated learning agent can, in principle, combine individual opinions and achieve collective benefit but the same agent cannot discount the escalation suggesting that one cognitive component of collective decision making in human may involve discounting of overconfidence arising from interactions.

Fuzzy adaptive iterative learning coordination control of second-order multi-agent systems with imprecise communication topology structure

NASA Astrophysics Data System (ADS)

Chen, Jiaxi; Li, Junmin

2018-02-01

In this paper, we investigate the perfect consensus problem for second-order linearly parameterised multi-agent systems (MAS) with imprecise communication topology structure. Takagi-Sugeno (T-S) fuzzy models are presented to describe the imprecise communication topology structure of leader-following MAS, and a distributed adaptive iterative learning control protocol is proposed with the dynamic of leader unknown to any of the agent. The proposed protocol guarantees that the follower agents can track the leader perfectly on [0,T] for the consensus problem. Under alignment condition, a sufficient condition of the consensus for closed-loop MAS is given based on Lyapunov stability theory. Finally, a numerical example and a multiple pendulum system are given to illustrate the effectiveness of the proposed algorithm.

Finding intrinsic rewards by embodied evolution and constrained reinforcement learning.

PubMed

Uchibe, Eiji; Doya, Kenji

2008-12-01

Understanding the design principle of reward functions is a substantial challenge both in artificial intelligence and neuroscience. Successful acquisition of a task usually requires not only rewards for goals, but also for intermediate states to promote effective exploration. This paper proposes a method for designing 'intrinsic' rewards of autonomous agents by combining constrained policy gradient reinforcement learning and embodied evolution. To validate the method, we use Cyber Rodent robots, in which collision avoidance, recharging from battery packs, and 'mating' by software reproduction are three major 'extrinsic' rewards. We show in hardware experiments that the robots can find appropriate 'intrinsic' rewards for the vision of battery packs and other robots to promote approach behaviors.

Scale-free memory model for multiagent reinforcement learning. Mean field approximation and rock-paper-scissors dynamics

NASA Astrophysics Data System (ADS)

Lubashevsky, I.; Kanemoto, S.

2010-07-01

A continuous time model for multiagent systems governed by reinforcement learning with scale-free memory is developed. The agents are assumed to act independently of one another in optimizing their choice of possible actions via trial-and-error search. To gain awareness about the action value the agents accumulate in their memory the rewards obtained from taking a specific action at each moment of time. The contribution of the rewards in the past to the agent current perception of action value is described by an integral operator with a power-law kernel. Finally a fractional differential equation governing the system dynamics is obtained. The agents are considered to interact with one another implicitly via the reward of one agent depending on the choice of the other agents. The pairwise interaction model is adopted to describe this effect. As a specific example of systems with non-transitive interactions, a two agent and three agent systems of the rock-paper-scissors type are analyzed in detail, including the stability analysis and numerical simulation. Scale-free memory is demonstrated to cause complex dynamics of the systems at hand. In particular, it is shown that there can be simultaneously two modes of the system instability undergoing subcritical and supercritical bifurcation, with the latter one exhibiting anomalous oscillations with the amplitude and period growing with time. Besides, the instability onset via this supercritical mode may be regarded as “altruism self-organization”. For the three agent system the instability dynamics is found to be rather irregular and can be composed of alternate fragments of oscillations different in their properties.

The involvement of model-based but not model-free learning signals during observational reward learning in the absence of choice.

PubMed

Dunne, Simon; D'Souza, Arun; O'Doherty, John P

2016-06-01

A major open question is whether computational strategies thought to be used during experiential learning, specifically model-based and model-free reinforcement learning, also support observational learning. Furthermore, the question of how observational learning occurs when observers must learn about the value of options from observing outcomes in the absence of choice has not been addressed. In the present study we used a multi-armed bandit task that encouraged human participants to employ both experiential and observational learning while they underwent functional magnetic resonance imaging (fMRI). We found evidence for the presence of model-based learning signals during both observational and experiential learning in the intraparietal sulcus. However, unlike during experiential learning, model-free learning signals in the ventral striatum were not detectable during this form of observational learning. These results provide insight into the flexibility of the model-based learning system, implicating this system in learning during observation as well as from direct experience, and further suggest that the model-free reinforcement learning system may be less flexible with regard to its involvement in observational learning. Copyright © 2016 the American Physiological Society.

Self-Learning Intelligent Agents for Dynamic Traffic Routing on Transportation Networks

NASA Astrophysics Data System (ADS)

Sadek, Add; Basha, Nagi

Intelligent Transportation Systems (ITS) are designed to take advantage of recent advances in communications, electronics, and Information Technology in improving the efficiency and safety of transportation systems. Among the several ITS applications is the notion of Dynamic Traffic Routing (DTR), which involves generating "optimal" routing recommendations to drivers with the aim of maximizing network utilizing. In this paper, we demonstrate the feasibility of using a self-learning intelligent agent to solve the DTR problem to achieve traffic user equilibrium in a transportation network. The core idea is to deploy an agent to a simulation model of a highway. The agent then learns by itself by interacting with the simulation model. Once the agent reaches a satisfactory level of performance, it can then be deployed to the real-world, where it would continue to learn how to refine its control policies over time. To test this concept in this paper, the Cell Transmission Model (CTM) developed by Carlos Daganzo of the University of California at Berkeley is used to simulate a simple highway with two main alternative routes. With the model developed, a Reinforcement Learning Agent (RLA) is developed to learn how to best dynamically route traffic, so as to maximize the utilization of existing capacity. Preliminary results obtained from our experiments are promising. RL, being an adaptive online learning technique, appears to have a great potential for controlling a stochastic dynamic systems such as a transportation system. Furthermore, the approach is highly scalable and applicable to a variety of networks and roadways.

Enhanced risk management by an emerging multi-agent architecture

NASA Astrophysics Data System (ADS)

Lin, Sin-Jin; Hsu, Ming-Fu

2014-07-01

Classification in imbalanced datasets has attracted much attention from researchers in the field of machine learning. Most existing techniques tend not to perform well on minority class instances when the dataset is highly skewed because they focus on minimising the forecasting error without considering the relative distribution of each class. This investigation proposes an emerging multi-agent architecture, grounded on cooperative learning, to solve the class-imbalanced classification problem. Additionally, this study deals further with the obscure nature of the multi-agent architecture and expresses comprehensive rules for auditors. The results from this study indicate that the presented model performs satisfactorily in risk management and is able to tackle a highly class-imbalanced dataset comparatively well. Furthermore, the knowledge visualised process, supported by real examples, can assist both internal and external auditors who must allocate limited detecting resources; they can take the rules as roadmaps to modify the auditing programme.

Multi-Objective Reinforcement Learning for Cognitive Radio-Based Satellite Communications

NASA Technical Reports Server (NTRS)

Ferreira, Paulo Victor R.; Paffenroth, Randy; Wyglinski, Alexander M.; Hackett, Timothy M.; Bilen, Sven G.; Reinhart, Richard C.; Mortensen, Dale J.

2016-01-01

Previous research on cognitive radios has addressed the performance of various machine-learning and optimization techniques for decision making of terrestrial link properties. In this paper, we present our recent investigations with respect to reinforcement learning that potentially can be employed by future cognitive radios installed onboard satellite communications systems specifically tasked with radio resource management. This work analyzes the performance of learning, reasoning, and decision making while considering multiple objectives for time-varying communications channels, as well as different cross-layer requirements. Based on the urgent demand for increased bandwidth, which is being addressed by the next generation of high-throughput satellites, the performance of cognitive radio is assessed considering links between a geostationary satellite and a fixed ground station operating at Ka-band (26 GHz). Simulation results show multiple objective performance improvements of more than 3.5 times for clear sky conditions and 6.8 times for rain conditions.

Multi-Objective Reinforcement Learning for Cognitive Radio Based Satellite Communications

NASA Technical Reports Server (NTRS)

Ferreira, Paulo; Paffenroth, Randy; Wyglinski, Alexander; Hackett, Timothy; Bilen, Sven; Reinhart, Richard; Mortensen, Dale John

2016-01-01

Previous research on cognitive radios has addressed the performance of various machine learning and optimization techniques for decision making of terrestrial link properties. In this paper, we present our recent investigations with respect to reinforcement learning that potentially can be employed by future cognitive radios installed onboard satellite communications systems specifically tasked with radio resource management. This work analyzes the performance of learning, reasoning, and decision making while considering multiple objectives for time-varying communications channels, as well as different crosslayer requirements. Based on the urgent demand for increased bandwidth, which is being addressed by the next generation of high-throughput satellites, the performance of cognitive radio is assessed considering links between a geostationary satellite and a fixed ground station operating at Ka-band (26 GHz). Simulation results show multiple objective performance improvements of more than 3:5 times for clear sky conditions and 6:8 times for rain conditions.

ICPL: Intelligent Cooperative Planning and Learning for Multi-agent Systems

DTIC Science & Technology

2012-02-29

objective was to develop a new planning approach for teams!of multiple UAVs that tightly integrates learning and cooperative!control algorithms at... algorithms at multiple levels of the planning architecture. The research results enabled a team of mobile agents to learn to adapt and react to uncertainty in...expressive representation that incorporates feature conjunctions. Our algorithm is simple to implement, fast to execute, and can be combined with any

Tungsten Disulfide Nanotubes Reinforced Biodegradable Polymers for Bone Tissue Engineering

PubMed Central

Lalwani, Gaurav; Henslee, Allan M.; Farshid, Behzad; Parmar, Priyanka; Lin, Liangjun; Qin, Yi-Xian; Kasper, F. Kurtis; Mikos, Antonios G.; Sitharaman, Balaji

2013-01-01

In this study, we have investigated the efficacy of inorganic nanotubes as reinforcing agents to improve the mechanical properties of poly(propylene fumarate) (PPF) composites as a function of nanomaterial loading concentration (0.01-0.2 wt%). Tungsten disulfide nanotubes (WSNTs) were used as reinforcing agents in the experimental groups. Single- and multi- walled carbon nanotubes (SWCNTs and MWCNTs) were used as positive controls, and crosslinked PPF composites were used as baseline control. Mechanical testing (compression and three-point bending) shows a significant enhancement (up to 28-190%) in the mechanical properties (compressive modulus, compressive yield strength, flexural modulus, and flexural yield strength) of WSNT reinforced PPF nanocomposites compared to the baseline control. In comparison to positive controls, at various concentrations, significant improvements in the mechanical properties of WSNT nanocomposites were also observed. In general, the inorganic nanotubes (WSNTs) showed a better (up to 127%) or equivalent mechanical reinforcement compared to carbon nanotubes (SWCNTs and MWCNTs). Sol fraction analysis showed significant increases in the crosslinking density of PPF in the presence of WSNTs (0.01-0.2 wt%). Transmission electron microscopy (TEM) analysis on thin sections of crosslinked nanocomposites showed the presence of WSNTs as individual nanotubes in the PPF matrix, whereas SWCNTs and MWCNTs existed as micron sized aggregates. The trend in the surface area of nanostructures obtained by BET surface area analysis was SWCNTs > MWCNTs > WSNTs. The BET surface area analysis, TEM analysis, and sol fraction analysis results taken together suggest that chemical composition (inorganic vs. carbon nanomaterials), presence of functional groups (such as sulfide and oxysulfide), and individual dispersion of the nanomaterials in the polymer matrix (absence of aggregation of the reinforcing agent) are the key parameters affecting the mechanical properties of nanostructure-reinforced PPF composites, and the reason for the observed increases in the mechanical properties compared to the baseline and positive controls. PMID:23727293

Functional Contour-following via Haptic Perception and Reinforcement Learning.

PubMed

Hellman, Randall B; Tekin, Cem; van der Schaar, Mihaela; Santos, Veronica J

2018-01-01

Many tasks involve the fine manipulation of objects despite limited visual feedback. In such scenarios, tactile and proprioceptive feedback can be leveraged for task completion. We present an approach for real-time haptic perception and decision-making for a haptics-driven, functional contour-following task: the closure of a ziplock bag. This task is challenging for robots because the bag is deformable, transparent, and visually occluded by artificial fingertip sensors that are also compliant. A deep neural net classifier was trained to estimate the state of a zipper within a robot's pinch grasp. A Contextual Multi-Armed Bandit (C-MAB) reinforcement learning algorithm was implemented to maximize cumulative rewards by balancing exploration versus exploitation of the state-action space. The C-MAB learner outperformed a benchmark Q-learner by more efficiently exploring the state-action space while learning a hard-to-code task. The learned C-MAB policy was tested with novel ziplock bag scenarios and contours (wire, rope). Importantly, this work contributes to the development of reinforcement learning approaches that account for limited resources such as hardware life and researcher time. As robots are used to perform complex, physically interactive tasks in unstructured or unmodeled environments, it becomes important to develop methods that enable efficient and effective learning with physical testbeds.

The Design of Collectives of Agents to Control Non-Markovian Systems

NASA Technical Reports Server (NTRS)

Lawson, John W.; Wolpert, David H.

2004-01-01

The Collective Intelligence (COIN) framework concerns the design of collectives of reinforcement-learning agents such that their interaction causes a provided "world" utility function concerning the entire collective to be maximized. Previously, we applied that framework to scenarios involving Markovian dynamics where no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. This approach sets the individual utility function of each agent to be both aligned with the world utility, and at the same time, easy for the associated agents to optimize. Here we extend that approach to systems involving non-Markovian dynamics. In computer simulations, we compare our techniques with each other and with conventional "team games". We show whereas in team games performance often degrades badly with time, it steadily improves when our techniques are used. We also investigate situations where the system's dimensionality is effectively reduced. We show that this leads to difficulties in the agents ability to learn. The implication is that learning is a property only of high-enough dimensional systems.

The Design of Collectives of Agents to Control Non-Markovian Systems

NASA Technical Reports Server (NTRS)

Lawson, John W.; Wolpert, David H.; Clancy, Daniel (Technical Monitor)

2002-01-01

The 'Collective Intelligence' (COIN) framework concerns the design of collectives of reinforcement-learning agents such that their interaction causes a provided 'world' utility function concerning the entire collective to be maximized. Previously, we applied that framework to scenarios involving Markovian dynamics where no re-evolution of the system from counter-factual initial conditions (an often expensive calculation) is permitted. This approach sets the individual utility function of each agent to be both aligned with the world utility, and at the same time, easy for the associated agents to optimize. Here we extend that approach to systems involving non-Markovian dynamics. In computer simulations, we compare our techniques with each other and with conventional-'team games'. We show whereas in team games performance often degrades badly with time, it steadily improves when our techniques are used. We also investigate situations where the system's dimensionality is effectively reduced. We show that this leads to difficulties in the agents' ability to learn. The implication is that 'learning' is a property only of high-enough dimensional systems.

Teacher Leadership--Connecting Learning to Practice

ERIC Educational Resources Information Center

Coughlan, Margaret

2015-01-01

The Common Core State Standards (CCSS, 2010) as the latest initiative in the ongoing effort of educational reform in the United States reinforces the need to build the capacity of teachers as leaders and change agents. As such, graduate teacher leadership programs function to support and develop teacher leadership praxis. Although studies of…

Chronic Heart Failure Follow-up Management Based on Agent Technology.

PubMed

Mohammadzadeh, Niloofar; Safdari, Reza

2015-10-01

Monitoring heart failure patients through continues assessment of sign and symptoms by information technology tools lead to large reduction in re-hospitalization. Agent technology is one of the strongest artificial intelligence areas; therefore, it can be expected to facilitate, accelerate, and improve health services especially in home care and telemedicine. The aim of this article is to provide an agent-based model for chronic heart failure (CHF) follow-up management. This research was performed in 2013-2014 to determine appropriate scenarios and the data required to monitor and follow-up CHF patients, and then an agent-based model was designed. Agents in the proposed model perform the following tasks: medical data access, communication with other agents of the framework and intelligent data analysis, including medical data processing, reasoning, negotiation for decision-making, and learning capabilities. The proposed multi-agent system has ability to learn and thus improve itself. Implementation of this model with more and various interval times at a broader level could achieve better results. The proposed multi-agent system is no substitute for cardiologists, but it could assist them in decision-making.

A study on expertise of agents and its effects on cooperative Q-learning.

PubMed

Araabi, Babak Nadjar; Mastoureshgh, Sahar; Ahmadabadi, Majid Nili

2007-04-01

Cooperation in learning (CL) can be realized in a multiagent system, if agents are capable of learning from both their own experiments and other agents' knowledge and expertise. Extra resources are exploited into higher efficiency and faster learning in CL as compared to that of individual learning (IL). In the real world, however, implementation of CL is not a straightforward task, in part due to possible differences in area of expertise (AOE). In this paper, reinforcement-learning homogenous agents are considered in an environment with multiple goals or tasks. As a result, they become expert in different domains with different amounts of expertness. Each agent uses a one-step Q-learning algorithm and is capable of exchanging its Q-table with those of its teammates. Two crucial questions are addressed in this paper: "How the AOE of an agent can be extracted?" and "How agents can improve their performance in CL by knowing their AOEs?" An algorithm is developed to extract the AOE based on state transitions as a gold standard from a behavioral point of view. Moreover, it is discussed that the AOE can be implicitly obtained through agents' expertness in the state level. Three new methods for CL through the combination of Q-tables are developed and examined for overall performance after CL. The performances of developed methods are compared with that of IL, strategy sharing (SS), and weighted SS (WSS). Obtained results show the superior performance of AOE-based methods as compared to that of existing CL methods, which do not use the notion of AOE. These results are very encouraging in support of the idea that "cooperation based on the AOE" performs better than the general CL methods.

Reinforcement learning interfaces for biomedical database systems.

PubMed

Rudowsky, I; Kulyba, O; Kunin, M; Parsons, S; Raphan, T

2006-01-01

Studies of neural function that are carried out in different laboratories and that address different questions use a wide range of descriptors for data storage, depending on the laboratory and the individuals that input the data. A common approach to describe non-textual data that are referenced through a relational database is to use metadata descriptors. We have recently designed such a prototype system, but to maintain efficiency and a manageable metadata table, free formatted fields were designed as table entries. The database interface application utilizes an intelligent agent to improve integrity of operation. The purpose of this study was to investigate how reinforcement learning algorithms can assist the user in interacting with the database interface application that has been developed to improve the performance of the system.

Multi-Agent Design and Implementation for an Online Peer Help System

ERIC Educational Resources Information Center

Meng, Anbo

2014-01-01

With the rapid advance of e-learning, the online peer help is playing increasingly important role. This paper explores the application of MAS to an online peer help system (MAPS). In the design phase, the architecture of MAPS is proposed, which consists of a set of agents including the personal agent, the course agent, the diagnosis agent, the DF…

An Immune Agent for Web-Based AI Course

ERIC Educational Resources Information Center

Gong, Tao; Cai, Zixing

2006-01-01

To overcome weakness and faults of a web-based e-learning course such as Artificial Intelligence (AI), an immune agent was proposed, simulating a natural immune mechanism against a virus. The immune agent was built on the multi-dimension education agent model and immune algorithm. The web-based AI course was comprised of many files, such as HTML…

A Multi-Agent Question-Answering System for E-Learning and Collaborative Learning Environment

ERIC Educational Resources Information Center

Alinaghi, Tannaz; Bahreininejad, Ardeshir

2011-01-01

The increasing advances of new Internet technologies in all application domains have changed life styles and interactions. E-learning and collaborative learning environment systems are originated through such changes and aim at providing facilities for people in different times and geographical locations to cooperate, collaborate, learn and work…

For whom will the Bayesian agents vote?

NASA Astrophysics Data System (ADS)

Caticha, Nestor; Cesar, Jonatas; Vicente, Renato

2015-04-01

Within an agent-based model where moral classifications are socially learned, we ask if a population of agents behaves in a way that may be compared with conservative or liberal positions in the real political spectrum. We assume that agents first experience a formative period, in which they adjust their learning style acting as supervised Bayesian adaptive learners. The formative phase is followed by a period of social influence by reinforcement learning. By comparing data generated by the agents with data from a sample of 15000 Moral Foundation questionnaires we found the following. 1. The number of information exchanges in the formative phase correlates positively with statistics identifying liberals in the social influence phase. This is consistent with recent evidence that connects the dopamine receptor D4-7R gene, political orientation and early age social clique size. 2. The learning algorithms that result from the formative phase vary in the way they treat novelty and corroborative information with more conservative-like agents treating it more equally than liberal-like agents. This is consistent with the correlation between political affiliation and the Openness personality trait reported in the literature. 3. Under the increase of a model parameter interpreted as an external pressure, the statistics of liberal agents resemble more those of conservative agents, consistent with reports on the consequences of external threats on measures of conservatism. We also show that in the social influence phase liberal-like agents readapt much faster than conservative-like agents when subjected to changes on the relevant set of moral issues. This suggests a verifiable dynamical criterium for attaching liberal or conservative labels to groups.

Learning Based Bidding Strategy for HVAC Systems in Double Auction Retail Energy Markets

DOE Office of Scientific and Technical Information (OSTI.GOV)

Sun, Yannan; Somani, Abhishek; Carroll, Thomas E.

In this paper, a bidding strategy is proposed using reinforcement learning for HVAC systems in a double auction market. The bidding strategy does not require a specific model-based representation of behavior, i.e., a functional form to translate indoor house temperatures into bid prices. The results from reinforcement learning based approach are compared with the HVAC bidding approach used in the AEP gridSMART® smart grid demonstration project and it is shown that the model-free (learning based) approach tracks well the results from the model-based behavior. Successful use of model-free approaches to represent device-level economic behavior may help develop similar approaches tomore » represent behavior of more complex devices or groups of diverse devices, such as in a building. Distributed control requires an understanding of decision making processes of intelligent agents so that appropriate mechanisms may be developed to control and coordinate their responses, and model-free approaches to represent behavior will be extremely useful in that quest.« less

Layered Learning in Multi-Agent Systems

DTIC Science & Technology

1998-12-15

project almost from the beginning has tirelessly experimented with different robot architectures, always managing to pull things together and create...TEAM MEMBER AGENT ARCHITECTURE I " ! Midfielder, Left : • i ) ( ^ J Goalie , Center Home Coordinates Home Range Max Range Figure

Does Feedback-Related Brain Response during Reinforcement Learning Predict Socio-motivational (In-)dependence in Adolescence?

PubMed Central

Raufelder, Diana; Boehme, Rebecca; Romund, Lydia; Golde, Sabrina; Lorenz, Robert C.; Gleich, Tobias; Beck, Anne

2016-01-01

This multi-methodological study applied functional magnetic resonance imaging to investigate neural activation in a group of adolescent students (N = 88) during a probabilistic reinforcement learning task. We related patterns of emerging brain activity and individual learning rates to socio-motivational (in-)dependence manifested in four different motivation types (MTs): (1) peer-dependent MT, (2) teacher-dependent MT, (3) peer-and-teacher-dependent MT, (4) peer-and-teacher-independent MT. A multinomial regression analysis revealed that the individual learning rate predicts students’ membership to the independent MT, or the peer-and-teacher-dependent MT. Additionally, the striatum, a brain region associated with behavioral adaptation and flexibility, showed increased learning-related activation in students with motivational independence. Moreover, the prefrontal cortex, which is involved in behavioral control, was more active in students of the peer-and-teacher-dependent MT. Overall, this study offers new insights into the interplay of motivation and learning with (1) a focus on inter-individual differences in the role of peers and teachers as source of students’ individual motivation and (2) its potential neurobiological basis. PMID:27199873

Artificial neural networks and approximate reasoning for intelligent control in space

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1991-01-01

A method is introduced for learning to refine the control rules of approximate reasoning-based controllers. A reinforcement-learning technique is used in conjunction with a multi-layer neural network model of an approximate reasoning-based controller. The model learns by updating its prediction of the physical system's behavior. The model can use the control knowledge of an experienced operator and fine-tune it through the process of learning. Some of the space domains suitable for applications of the model such as rendezvous and docking, camera tracking, and tethered systems control are discussed.

Chronic Heart Failure Follow-up Management Based on Agent Technology

PubMed Central

Safdari, Reza

2015-01-01

Objectives Monitoring heart failure patients through continues assessment of sign and symptoms by information technology tools lead to large reduction in re-hospitalization. Agent technology is one of the strongest artificial intelligence areas; therefore, it can be expected to facilitate, accelerate, and improve health services especially in home care and telemedicine. The aim of this article is to provide an agent-based model for chronic heart failure (CHF) follow-up management. Methods This research was performed in 2013-2014 to determine appropriate scenarios and the data required to monitor and follow-up CHF patients, and then an agent-based model was designed. Results Agents in the proposed model perform the following tasks: medical data access, communication with other agents of the framework and intelligent data analysis, including medical data processing, reasoning, negotiation for decision-making, and learning capabilities. Conclusions The proposed multi-agent system has ability to learn and thus improve itself. Implementation of this model with more and various interval times at a broader level could achieve better results. The proposed multi-agent system is no substitute for cardiologists, but it could assist them in decision-making. PMID:26618038

Evolution of learning and levels of selection: A lesson from avian parent-offspring communication.

PubMed

Lotem, Arnon; Biran-Yoeli, Inbar

2013-09-20

In recent years, it has become increasingly clear that the evolution of behavior may be better understood as the evolution of the learning mechanisms that produce it, and that such mechanisms should be modeled and tested explicitly. However, this approach, which has recently been applied to animal foraging and decision-making, has rarely been applied to the social and communicative behaviors that are likely to operate in complex social environments and be subject to multi-level selection. Here we use genetic, agent-based evolutionary simulations to explore how learning mechanisms may evolve to adjust the level of nestling begging (offspring signaling of need), and to examine the possible consequences of this process for parent-offspring conflict and communication. In doing so, we also provide the first step-by-step dynamic model of parent-offspring communication. The results confirm several previous theoretical predictions and demonstrate three novel phenomena. First, negatively frequency-dependent group-level selection can generate a stable polymorphism of learning strategies and parental responses. Second, while conventional reinforcement learning models fail to cope successfully with family dynamics at the nest, a newly developed learning model (incorporating behaviors that are consistent with recent experimental results on learning in nestling begging) produced effective learning, which evolved successfully. Third, while kin-selection affects the frequency of the different learning genes, its impact on begging slope and intensity was unexpectedly negligible, demonstrating that evolution is a complex process, and showing that the effect of kin-selection on behaviors that are shaped by learning may not be predicted by simple application of Hamilton's rule. Copyright © 2013 Elsevier Inc. All rights reserved.

Evolution of learning and levels of selection: a lesson from avian parent-offspring communication.

PubMed

Lotem, Arnon; Biran-Yoeli, Inbar

2014-02-01

In recent years, it has become increasingly clear that the evolution of behavior may be better understood as the evolution of the learning mechanisms that produce it, and that such mechanisms should be modeled and tested explicitly. However, this approach, which has recently been applied to animal foraging and decision-making, has rarely been applied to the social and communicative behaviors that are likely to operate in complex social environments and be subject to multi-level selection. Here we use genetic, agent-based evolutionary simulations to explore how learning mechanisms may evolve to adjust the level of nestling begging (offspring signaling of need), and to examine the possible consequences of this process for parent-offspring conflict and communication. In doing so, we also provide the first step-by-step dynamic model of parent-offspring communication. The results confirm several previous theoretical predictions and demonstrate three novel phenomena. First, negatively frequency-dependent group-level selection can generate a stable polymorphism of learning strategies and parental responses. Second, while conventional reinforcement learning models fail to cope successfully with family dynamics at the nest, a newly developed learning model (incorporating behaviors that are consistent with recent experimental results on learning in nestling begging) produced effective learning, which evolved successfully. Third, while kin-selection affects the frequency of the different learning genes, its impact on begging slope and intensity was unexpectedly negligible, demonstrating that evolution is a complex process, and showing that the effect of kin-selection on behaviors that are shaped by learning may not be predicted by simple application of Hamilton's rule. Copyright © 2013 Elsevier Inc. All rights reserved.

A Survey of Collective Intelligence

NASA Technical Reports Server (NTRS)

Wolpert, David H.; Tumer, Kagan

1999-01-01

This chapter presents the science of "COllective INtelligence" (COIN). A COIN is a large multi-agent systems where: i) the agents each run reinforcement learning (RL) algorithms; ii) there is little to no centralized communication or control; iii) there is a provided world utility function that, rates the possible histories of tile full system. Tile conventional approach to designing large distributed systems to optimize a world utility does not use agents running RL algorithms. Rather that approach begins with explicit modeling of the overall system's dynamics, followed by detailed hand-tuning of the interactions between the components to ensure that they "cooperate" as far as the world utility is concerned. This approach is labor-intensive, often results in highly non-robust systems, and usually results in design techniques that, have limited applicability. In contrast, with COINs we wish to solve the system design problems implicitly, via the 'adaptive' character of the RL algorithms of each of the agents. This COIN approach introduces an entirely new, profound design problem: Assuming the RL algorithms are able to achieve high rewards, what reward functions for the individual agents will, when pursued by those agents, result in high world utility? In other words, what reward functions will best ensure that we do not have phenomena like the tragedy of the commons, or Braess's paradox? Although still very young, the science of COINs has already resulted in successes in artificial domains, in particular in packet-routing, the leader-follower problem, and in variants of Arthur's "El Farol bar problem". It is expected that as it matures not only will COIN science expand greatly the range of tasks addressable by human engineers, but it will also provide much insight into already established scientific fields, such as economics, game theory, or population biology.

Preparation and characterization of bagasse/HDPE composites using multi-walled carbon nanotubes.

PubMed

Ashori, Alireza; Sheshmani, Shabnam; Farhani, Foad

2013-01-30

This article presents the preparation and characterization of bagasse/high density polyethylene (HDPE) composites. The effects of multi-walled carbon nanotubes (MWCNTs), as reinforcing agent, on the mechanical and physical properties were also investigated. In order to increase the interphase adhesion, maleic anhydride grafted polyethylene (MAPE) was added as a coupling agent to all the composites studied. In the sample preparation, MWCNTs and MAPE contents were used as variable factors. The morphology of the specimens was characterized using scanning electron microscopy (SEM) technique. The results of strength measurement indicated that when 1.5 wt% MWCNTs were added, tensile and flexural properties reached their maximum values. At high level of MWCNTs loading (3 or 4 wt%), increased population of MWCNTs lead to agglomeration and stress transfer gets blocked. The addition of MWCNTs filler slightly decreased the impact strength of composites. Both mechanical and physical properties were improved when 4 wt% MAPE was applied. SEM micrographs also showed that the surface roughness improved with increasing MAPE loading from 0 to 4 wt%. The improvement of physicomechanical properties of composites confirmed that MWCNTs have good reinforcement and the optimum synergistic effect of MWCNTs and MAPE was achieved at the combination of 1.5 and 4 wt%, respectively. Copyright © 2012 Elsevier Ltd. All rights reserved.

Learning-based traffic signal control algorithms with neighborhood information sharing: An application for sustainable mobility

DOE Office of Scientific and Technical Information (OSTI.GOV)

Aziz, H. M. Abdul; Zhu, Feng; Ukkusuri, Satish V.

Here, this research applies R-Markov Average Reward Technique based reinforcement learning (RL) algorithm, namely RMART, for vehicular signal control problem leveraging information sharing among signal controllers in connected vehicle environment. We implemented the algorithm in a network of 18 signalized intersections and compare the performance of RMART with fixed, adaptive, and variants of the RL schemes. Results show significant improvement in system performance for RMART algorithm with information sharing over both traditional fixed signal timing plans and real time adaptive control schemes. Additionally, the comparison with reinforcement learning algorithms including Q learning and SARSA indicate that RMART performs better atmore » higher congestion levels. Further, a multi-reward structure is proposed that dynamically adjusts the reward function with varying congestion states at the intersection. Finally, the results from test networks show significant reduction in emissions (CO, CO 2, NO x, VOC, PM 10) when RL algorithms are implemented compared to fixed signal timings and adaptive schemes.« less

Performance Enhancement Using Selective Reinforcement for Metallic Single- and Multi-Pin Loaded Holes

NASA Technical Reports Server (NTRS)

Farley, Gary L.; Seshadri, Banavara R.

2005-01-01

An analysis based investigation of aluminum with metal matrix composite selectively reinforced single- and multi-hole specimens was performed and their results compared with results from geometrically comparable non-reinforced specimens. All reinforced specimens exhibited a significant increase in performance. Performance increase of up to 170 percent was achieved. Specimen failure modes were consistent with results from reinforced polymeric matrix composite specimens. Localized reinforcement application (circular) proved as effective as a broader area (strip) reinforcement. Also, selective reinforcement is an excellent method of increasing the performance of multi-hole specimens.

Reinforcing the Cycle of Assessment

ERIC Educational Resources Information Center

Harhai, Marilyn K.; Krueger, Janice M.

2014-01-01

Purpose: The purpose of this study was to examine the effectiveness of the Multi-Subject Learning Survey (MSLS) as an assessment instrument for graduate students. Methodology: The MSLS was administered as a pre-test to 124 students enrolled in the introductory course for the Master of Science in Library Science degree at an American Library…

Overtaking method based on sand-sifter mechanism: Why do optimistic value functions find optimal solutions in multi-armed bandit problems?

PubMed

Ochi, Kento; Kamiura, Moto

2015-09-01

A multi-armed bandit problem is a search problem on which a learning agent must select the optimal arm among multiple slot machines generating random rewards. UCB algorithm is one of the most popular methods to solve multi-armed bandit problems. It achieves logarithmic regret performance by coordinating balance between exploration and exploitation. Since UCB algorithms, researchers have empirically known that optimistic value functions exhibit good performance in multi-armed bandit problems. The terms optimistic or optimism might suggest that the value function is sufficiently larger than the sample mean of rewards. The first definition of UCB algorithm is focused on the optimization of regret, and it is not directly based on the optimism of a value function. We need to think the reason why the optimism derives good performance in multi-armed bandit problems. In the present article, we propose a new method, which is called Overtaking method, to solve multi-armed bandit problems. The value function of the proposed method is defined as an upper bound of a confidence interval with respect to an estimator of expected value of reward: the value function asymptotically approaches to the expected value of reward from the upper bound. If the value function is larger than the expected value under the asymptote, then the learning agent is almost sure to be able to obtain the optimal arm. This structure is called sand-sifter mechanism, which has no regrowth of value function of suboptimal arms. It means that the learning agent can play only the current best arm in each time step. Consequently the proposed method achieves high accuracy rate and low regret and some value functions of it can outperform UCB algorithms. This study suggests the advantage of optimism of agents in uncertain environment by one of the simplest frameworks. Copyright © 2015 The Authors. Published by Elsevier Ireland Ltd.. All rights reserved.

Interactive machine learning for health informatics: when do we need the human-in-the-loop?

PubMed

Holzinger, Andreas

2016-06-01

Machine learning (ML) is the fastest growing field in computer science, and health informatics is among the greatest challenges. The goal of ML is to develop algorithms which can learn and improve over time and can be used for predictions. Most ML researchers concentrate on automatic machine learning (aML), where great advances have been made, for example, in speech recognition, recommender systems, or autonomous vehicles. Automatic approaches greatly benefit from big data with many training sets. However, in the health domain, sometimes we are confronted with a small number of data sets or rare events, where aML-approaches suffer of insufficient training samples. Here interactive machine learning (iML) may be of help, having its roots in reinforcement learning, preference learning, and active learning. The term iML is not yet well used, so we define it as "algorithms that can interact with agents and can optimize their learning behavior through these interactions, where the agents can also be human." This "human-in-the-loop" can be beneficial in solving computationally hard problems, e.g., subspace clustering, protein folding, or k-anonymization of health data, where human expertise can help to reduce an exponential search space through heuristic selection of samples. Therefore, what would otherwise be an NP-hard problem, reduces greatly in complexity through the input and the assistance of a human agent involved in the learning phase.

Efficiency Improvement of Action Acquisition in Two-Link Robot Arm Using Fuzzy ART with Genetic Algorithm

NASA Astrophysics Data System (ADS)

Kotani, Naoki; Taniguchi, Kenji

An efficient learning method using Fuzzy ART with Genetic Algorithm is proposed. The proposed method reduces the number of trials by using a policy acquired in other tasks because a reinforcement learning needs a lot of the number of trials until an agent acquires appropriate actions. Fuzzy ART is an incremental unsupervised learning algorithm in responce to arbitrary sequences of analog or binary input vectors. Our proposed method gives a policy by crossover or mutation when an agent observes unknown states. Selection controls the category proliferation problem of Fuzzy ART. The effectiveness of the proposed method was verified with the simulation of the reaching problem for the two-link robot arm. The proposed method achieves a reduction of both the number of trials and the number of states.

Learning from Noisy and Delayed Rewards: The Value of Reinforcement Learning to Defense Modeling and Simulation

DTIC Science & Technology

2012-09-01

following 500 trials with 1000 replications with single reward upon attainment of the goal state by algorithm and policy. DQ- C with -greedy obtained...aspects of the civilian population rather than combat forces. These agents rep- resent not a single human, but a population segment. Similar...TD(λ) combines elements of MC and TD methods into a single framework to estimate the value of each state, V(s), through the use of eligibility traces

Acute Δ-9-tetrahydrocannabinol administration in female rats attenuates immediate responses following losses but not multi-trial reinforcement learning from wins.

PubMed

Wong, Scott A; Randolph, Sienna H; Ivan, Victorita E; Gruber, Aaron J

2017-09-29

Δ-9-Tetrahydrocannabinol (THC) is the main psychoactive component of marijuana and has potent effects on decision-making, including a proposed reduction in cognitive flexibility. We demonstrate here that acute THC administration differentially affects some of the processes that contribute to cognitive flexibility. Specifically, THC reduces lose-shift responding in which female rats tend to immediately shift choice responses away from options that result in reward omission on the previous trial. THC, however, did not impair the ability of rats to flexibly bias responses toward feeders with higher probability of reward in a reversal task. This response adaptation developed over several trials, suggesting that THC did not impair slower forms of reinforcement learning needed to choose among options with unequal utility. This dissociation of THC's effects on innate/rapid and learned/gradual decision-making processes was unexpected, but is supported by emerging evidence that lose-shift responding is mediated by neural mechanisms distinct from those involved in other forms of reinforcement learning. The present data suggest that, at least in some tasks, the apparent reductions in cognitive flexibility by THC may be explained by the immediate effects on loss sensitivity, rather than impairments of all processes used for choice adaptation. Copyright © 2017 Elsevier B.V. All rights reserved.

A Self-Adaptive Multi-Agent System Approach for Collaborative Mobile Learning

ERIC Educational Resources Information Center

de la Iglesia, Didac Gil; Calderon, Juan Felipe; Weyns, Danny; Milrad, Marcelo; Nussbaum, Miguel

2015-01-01

Mobile technologies have emerged as facilitators in the learning process, extending traditional classroom activities. However, engineering mobile learning applications for outdoor usage poses severe challenges. The requirements of these applications are challenging, as many different aspects need to be catered, such as resource access and sharing,…

A Measure of Real-Time Intelligence

NASA Astrophysics Data System (ADS)

Gavane, Vaibhav

2013-03-01

We propose a new measure of intelligence for general reinforcement learning agents, based on the notion that an agent's environment can change at any step of execution of the agent. That is, an agent is considered to be interacting with its environment in real-time. In this sense, the resulting intelligence measure is more general than the universal intelligence measure (Legg and Hutter, 2007) and the anytime universal intelligence test (Hernández-Orallo and Dowe, 2010). A major advantage of the measure is that an agent's computational complexity is factored into the measure in a natural manner. We show that there exist agents with intelligence arbitrarily close to the theoretical maximum, and that the intelligence of agents depends on their parallel processing capability. We thus believe that the measure can provide a better evaluation of agents and guidance for building practical agents with high intelligence.

Application of Fuzzy State Aggregation and Policy Hill Climbing to Multi-Agent Systems in Stochastic Environments

DTIC Science & Technology

2006-03-01

represented by the set of tiles that it lies in. A variation on tile coding is Berenji and Vengerov’s [4, 5] use of fuzzy state aggregation (FSA) as a means...approximation with Q-learning is not a new or unusual concept [1, 3]. Berenji and Vengerov [4, 5] advanced this work in their application of Q-learning and... Berenji and Vengerov [4, 5]. The simplified Tileworld consists of agents, reward spikes, and deformations. The agent must select which reward to pursue

Knowledge-Based Reinforcement Learning for Data Mining

NASA Astrophysics Data System (ADS)

Kudenko, Daniel; Grzes, Marek

Data Mining is the process of extracting patterns from data. Two general avenues of research in the intersecting areas of agents and data mining can be distinguished. The first approach is concerned with mining an agent’s observation data in order to extract patterns, categorize environment states, and/or make predictions of future states. In this setting, data is normally available as a batch, and the agent’s actions and goals are often independent of the data mining task. The data collection is mainly considered as a side effect of the agent’s activities. Machine learning techniques applied in such situations fall into the class of supervised learning. In contrast, the second scenario occurs where an agent is actively performing the data mining, and is responsible for the data collection itself. For example, a mobile network agent is acquiring and processing data (where the acquisition may incur a certain cost), or a mobile sensor agent is moving in a (perhaps hostile) environment, collecting and processing sensor readings. In these settings, the tasks of the agent and the data mining are highly intertwined and interdependent (or even identical). Supervised learning is not a suitable technique for these cases. Reinforcement Learning (RL) enables an agent to learn from experience (in form of reward and punishment for explorative actions) and adapt to new situations, without a teacher. RL is an ideal learning technique for these data mining scenarios, because it fits the agent paradigm of continuous sensing and acting, and the RL agent is able to learn to make decisions on the sampling of the environment which provides the data. Nevertheless, RL still suffers from scalability problems, which have prevented its successful use in many complex real-world domains. The more complex the tasks, the longer it takes a reinforcement learning algorithm to converge to a good solution. For many real-world tasks, human expert knowledge is available. For example, human experts have developed heuristics that help them in planning and scheduling resources in their work place. However, this domain knowledge is often rough and incomplete. When the domain knowledge is used directly by an automated expert system, the solutions are often sub-optimal, due to the incompleteness of the knowledge, the uncertainty of environments, and the possibility to encounter unexpected situations. RL, on the other hand, can overcome the weaknesses of the heuristic domain knowledge and produce optimal solutions. In the talk we propose two techniques, which represent first steps in the area of knowledge-based RL (KBRL). The first technique [1] uses high-level STRIPS operator knowledge in reward shaping to focus the search for the optimal policy. Empirical results show that the plan-based reward shaping approach outperforms other RL techniques, including alternative manual and MDP-based reward shaping when it is used in its basic form. We showed that MDP-based reward shaping may fail and successful experiments with STRIPS-based shaping suggest modifications which can overcome encountered problems. The STRIPSbased method we propose allows expressing the same domain knowledge in a different way and the domain expert can choose whether to define an MDP or STRIPS planning task. We also evaluated the robustness of the proposed STRIPS-based technique to errors in the plan knowledge. In case that STRIPS knowledge is not available, we propose a second technique [2] that shapes the reward with hierarchical tile coding. Where the Q-function is represented with low-level tile coding, a V-function with coarser tile coding can be learned in parallel and used to approximate the potential for ground states. In the context of data mining, our KBRL approaches can also be used for any data collection task where the acquisition of data may incur considerable cost. In addition, observing the data collection agent in specific scenarios may lead to new insights into optimal data collection behaviour in the respective domains. In future work, we intend to demonstrate and evaluate our techniques on concrete real-world data mining applications.

A Reinforcement Learning Model Equipped with Sensors for Generating Perception Patterns: Implementation of a Simulated Air Navigation System Using ADS-B (Automatic Dependent Surveillance-Broadcast) Technology.

PubMed

Álvarez de Toledo, Santiago; Anguera, Aurea; Barreiro, José M; Lara, Juan A; Lizcano, David

2017-01-19

Over the last few decades, a number of reinforcement learning techniques have emerged, and different reinforcement learning-based applications have proliferated. However, such techniques tend to specialize in a particular field. This is an obstacle to their generalization and extrapolation to other areas. Besides, neither the reward-punishment (r-p) learning process nor the convergence of results is fast and efficient enough. To address these obstacles, this research proposes a general reinforcement learning model. This model is independent of input and output types and based on general bioinspired principles that help to speed up the learning process. The model is composed of a perception module based on sensors whose specific perceptions are mapped as perception patterns. In this manner, similar perceptions (even if perceived at different positions in the environment) are accounted for by the same perception pattern. Additionally, the model includes a procedure that statistically associates perception-action pattern pairs depending on the positive or negative results output by executing the respective action in response to a particular perception during the learning process. To do this, the model is fitted with a mechanism that reacts positively or negatively to particular sensory stimuli in order to rate results. The model is supplemented by an action module that can be configured depending on the maneuverability of each specific agent. The model has been applied in the air navigation domain, a field with strong safety restrictions, which led us to implement a simulated system equipped with the proposed model. Accordingly, the perception sensors were based on Automatic Dependent Surveillance-Broadcast (ADS-B) technology, which is described in this paper. The results were quite satisfactory, and it outperformed traditional methods existing in the literature with respect to learning reliability and efficiency.

A Reinforcement Learning Model Equipped with Sensors for Generating Perception Patterns: Implementation of a Simulated Air Navigation System Using ADS-B (Automatic Dependent Surveillance-Broadcast) Technology

PubMed Central

Álvarez de Toledo, Santiago; Anguera, Aurea; Barreiro, José M.; Lara, Juan A.; Lizcano, David

2017-01-01

Over the last few decades, a number of reinforcement learning techniques have emerged, and different reinforcement learning-based applications have proliferated. However, such techniques tend to specialize in a particular field. This is an obstacle to their generalization and extrapolation to other areas. Besides, neither the reward-punishment (r-p) learning process nor the convergence of results is fast and efficient enough. To address these obstacles, this research proposes a general reinforcement learning model. This model is independent of input and output types and based on general bioinspired principles that help to speed up the learning process. The model is composed of a perception module based on sensors whose specific perceptions are mapped as perception patterns. In this manner, similar perceptions (even if perceived at different positions in the environment) are accounted for by the same perception pattern. Additionally, the model includes a procedure that statistically associates perception-action pattern pairs depending on the positive or negative results output by executing the respective action in response to a particular perception during the learning process. To do this, the model is fitted with a mechanism that reacts positively or negatively to particular sensory stimuli in order to rate results. The model is supplemented by an action module that can be configured depending on the maneuverability of each specific agent. The model has been applied in the air navigation domain, a field with strong safety restrictions, which led us to implement a simulated system equipped with the proposed model. Accordingly, the perception sensors were based on Automatic Dependent Surveillance-Broadcast (ADS-B) technology, which is described in this paper. The results were quite satisfactory, and it outperformed traditional methods existing in the literature with respect to learning reliability and efficiency. PMID:28106849

Learning Natural Selection in 4th Grade with Multi-Agent-Based Computational Models

NASA Astrophysics Data System (ADS)

Dickes, Amanda Catherine; Sengupta, Pratim

2013-06-01

In this paper, we investigate how elementary school students develop multi-level explanations of population dynamics in a simple predator-prey ecosystem, through scaffolded interactions with a multi-agent-based computational model (MABM). The term "agent" in an MABM indicates individual computational objects or actors (e.g., cars), and these agents obey simple rules assigned or manipulated by the user (e.g., speeding up, slowing down, etc.). It is the interactions between these agents, based on the rules assigned by the user, that give rise to emergent, aggregate-level behavior (e.g., formation and movement of the traffic jam). Natural selection is such an emergent phenomenon, which has been shown to be challenging for novices (K16 students) to understand. Whereas prior research on learning evolutionary phenomena with MABMs has typically focused on high school students and beyond, we investigate how elementary students (4th graders) develop multi-level explanations of some introductory aspects of natural selection—species differentiation and population change—through scaffolded interactions with an MABM that simulates predator-prey dynamics in a simple birds-butterflies ecosystem. We conducted a semi-clinical interview based study with ten participants, in which we focused on the following: a) identifying the nature of learners' initial interpretations of salient events or elements of the represented phenomena, b) identifying the roles these interpretations play in the development of their multi-level explanations, and c) how attending to different levels of the relevant phenomena can make explicit different mechanisms to the learners. In addition, our analysis also shows that although there were differences between high- and low-performing students (in terms of being able to explain population-level behaviors) in the pre-test, these differences disappeared in the post-test.

Imitation learning based on an intrinsic motivation mechanism for efficient coding

PubMed Central

Triesch, Jochen

2013-01-01

A hypothesis regarding the development of imitation learning is presented that is rooted in intrinsic motivations. It is derived from a recently proposed form of intrinsically motivated learning (IML) for efficient coding in active perception, wherein an agent learns to perform actions with its sense organs to facilitate efficient encoding of the sensory data. To this end, actions of the sense organs that improve the encoding of the sensory data trigger an internally generated reinforcement signal. Here it is argued that the same IML mechanism might also support the development of imitation when general actions beyond those of the sense organs are considered: The learner first observes a tutor performing a behavior and learns a model of the the behavior's sensory consequences. The learner then acts itself and receives an internally generated reinforcement signal reflecting how well the sensory consequences of its own behavior are encoded by the sensory model. Actions that are more similar to those of the tutor will lead to sensory signals that are easier to encode and produce a higher reinforcement signal. Through this, the learner's behavior is progressively tuned to make the sensory consequences of its actions match the learned sensory model. I discuss this mechanism in the context of human language acquisition and bird song learning where similar ideas have been proposed. The suggested mechanism also offers an account for the development of mirror neurons and makes a number of predictions. Overall, it establishes a connection between principles of efficient coding, intrinsic motivations and imitation. PMID:24204350

Autonomous Motion Learning for Intra-Vehicular Activity Space Robot

NASA Astrophysics Data System (ADS)

Watanabe, Yutaka; Yairi, Takehisa; Machida, Kazuo

Space robots will be needed in the future space missions. So far, many types of space robots have been developed, but in particular, Intra-Vehicular Activity (IVA) space robots that support human activities should be developed to reduce human-risks in space. In this paper, we study the motion learning method of an IVA space robot with the multi-link mechanism. The advantage point is that this space robot moves using reaction force of the multi-link mechanism and contact forces from the wall as space walking of an astronaut, not to use a propulsion. The control approach is determined based on a reinforcement learning with the actor-critic algorithm. We demonstrate to clear effectiveness of this approach using a 5-link space robot model by simulation. First, we simulate that a space robot learn the motion control including contact phase in two dimensional case. Next, we simulate that a space robot learn the motion control changing base attitude in three dimensional case.

An architecture for designing fuzzy logic controllers using neural networks

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1991-01-01

Described here is an architecture for designing fuzzy controllers through a hierarchical process of control rule acquisition and by using special classes of neural network learning techniques. A new method for learning to refine a fuzzy logic controller is introduced. A reinforcement learning technique is used in conjunction with a multi-layer neural network model of a fuzzy controller. The model learns by updating its prediction of the plant's behavior and is related to the Sutton's Temporal Difference (TD) method. The method proposed here has the advantage of using the control knowledge of an experienced operator and fine-tuning it through the process of learning. The approach is applied to a cart-pole balancing system.

Switching Reinforcement Learning for Continuous Action Space

NASA Astrophysics Data System (ADS)

Nagayoshi, Masato; Murao, Hajime; Tamaki, Hisashi

Reinforcement Learning (RL) attracts much attention as a technique of realizing computational intelligence such as adaptive and autonomous decentralized systems. In general, however, it is not easy to put RL into practical use. This difficulty includes a problem of designing a suitable action space of an agent, i.e., satisfying two requirements in trade-off: (i) to keep the characteristics (or structure) of an original search space as much as possible in order to seek strategies that lie close to the optimal, and (ii) to reduce the search space as much as possible in order to expedite the learning process. In order to design a suitable action space adaptively, we propose switching RL model to mimic a process of an infant's motor development in which gross motor skills develop before fine motor skills. Then, a method for switching controllers is constructed by introducing and referring to the “entropy”. Further, through computational experiments by using robot navigation problems with one and two-dimensional continuous action space, the validity of the proposed method has been confirmed.

Adaptive critic autopilot design of bank-to-turn missiles using fuzzy basis function networks.

PubMed

Lin, Chuan-Kai

2005-04-01

A new adaptive critic autopilot design for bank-to-turn missiles is presented. In this paper, the architecture of adaptive critic learning scheme contains a fuzzy-basis-function-network based associative search element (ASE), which is employed to approximate nonlinear and complex functions of bank-to-turn missiles, and an adaptive critic element (ACE) generating the reinforcement signal to tune the associative search element. In the design of the adaptive critic autopilot, the control law receives signals from a fixed gain controller, an ASE and an adaptive robust element, which can eliminate approximation errors and disturbances. Traditional adaptive critic reinforcement learning is the problem faced by an agent that must learn behavior through trial-and-error interactions with a dynamic environment, however, the proposed tuning algorithm can significantly shorten the learning time by online tuning all parameters of fuzzy basis functions and weights of ASE and ACE. Moreover, the weight updating law derived from the Lyapunov stability theory is capable of guaranteeing both tracking performance and stability. Computer simulation results confirm the effectiveness of the proposed adaptive critic autopilot.

Generating Adaptive Behaviour within a Memory-Prediction Framework

PubMed Central

Rawlinson, David; Kowadlo, Gideon

2012-01-01

The Memory-Prediction Framework (MPF) and its Hierarchical-Temporal Memory implementation (HTM) have been widely applied to unsupervised learning problems, for both classification and prediction. To date, there has been no attempt to incorporate MPF/HTM in reinforcement learning or other adaptive systems; that is, to use knowledge embodied within the hierarchy to control a system, or to generate behaviour for an agent. This problem is interesting because the human neocortex is believed to play a vital role in the generation of behaviour, and the MPF is a model of the human neocortex. We propose some simple and biologically-plausible enhancements to the Memory-Prediction Framework. These cause it to explore and interact with an external world, while trying to maximize a continuous, time-varying reward function. All behaviour is generated and controlled within the MPF hierarchy. The hierarchy develops from a random initial configuration by interaction with the world and reinforcement learning only. Among other demonstrations, we show that a 2-node hierarchy can learn to successfully play “rocks, paper, scissors” against a predictable opponent. PMID:22272231

Effective reinforcement learning following cerebellar damage requires a balance between exploration and motor noise.

PubMed

Therrien, Amanda S; Wolpert, Daniel M; Bastian, Amy J

2016-01-01

Reinforcement and error-based processes are essential for motor learning, with the cerebellum thought to be required only for the error-based mechanism. Here we examined learning and retention of a reaching skill under both processes. Control subjects learned similarly from reinforcement and error-based feedback, but showed much better retention under reinforcement. To apply reinforcement to cerebellar patients, we developed a closed-loop reinforcement schedule in which task difficulty was controlled based on recent performance. This schedule produced substantial learning in cerebellar patients and controls. Cerebellar patients varied in their learning under reinforcement but fully retained what was learned. In contrast, they showed complete lack of retention in error-based learning. We developed a mechanistic model of the reinforcement task and found that learning depended on a balance between exploration variability and motor noise. While the cerebellar and control groups had similar exploration variability, the patients had greater motor noise and hence learned less. Our results suggest that cerebellar damage indirectly impairs reinforcement learning by increasing motor noise, but does not interfere with the reinforcement mechanism itself. Therefore, reinforcement can be used to learn and retain novel skills, but optimal reinforcement learning requires a balance between exploration variability and motor noise. © The Author (2015). Published by Oxford University Press on behalf of the Guarantors of Brain.

Effective reinforcement learning following cerebellar damage requires a balance between exploration and motor noise

PubMed Central

Therrien, Amanda S.; Wolpert, Daniel M.

2016-01-01

Abstract See Miall and Galea (doi: 10.1093/awv343 ) for a scientific commentary on this article. Reinforcement and error-based processes are essential for motor learning, with the cerebellum thought to be required only for the error-based mechanism. Here we examined learning and retention of a reaching skill under both processes. Control subjects learned similarly from reinforcement and error-based feedback, but showed much better retention under reinforcement. To apply reinforcement to cerebellar patients, we developed a closed-loop reinforcement schedule in which task difficulty was controlled based on recent performance. This schedule produced substantial learning in cerebellar patients and controls. Cerebellar patients varied in their learning under reinforcement but fully retained what was learned. In contrast, they showed complete lack of retention in error-based learning. We developed a mechanistic model of the reinforcement task and found that learning depended on a balance between exploration variability and motor noise. While the cerebellar and control groups had similar exploration variability, the patients had greater motor noise and hence learned less. Our results suggest that cerebellar damage indirectly impairs reinforcement learning by increasing motor noise, but does not interfere with the reinforcement mechanism itself. Therefore, reinforcement can be used to learn and retain novel skills, but optimal reinforcement learning requires a balance between exploration variability and motor noise. PMID:26626368

Risk-sensitive reinforcement learning.

PubMed

Shen, Yun; Tobia, Michael J; Sommer, Tobias; Obermayer, Klaus

2014-07-01

We derive a family of risk-sensitive reinforcement learning methods for agents, who face sequential decision-making tasks in uncertain environments. By applying a utility function to the temporal difference (TD) error, nonlinear transformations are effectively applied not only to the received rewards but also to the true transition probabilities of the underlying Markov decision process. When appropriate utility functions are chosen, the agents' behaviors express key features of human behavior as predicted by prospect theory (Kahneman & Tversky, 1979 ), for example, different risk preferences for gains and losses, as well as the shape of subjective probability curves. We derive a risk-sensitive Q-learning algorithm, which is necessary for modeling human behavior when transition probabilities are unknown, and prove its convergence. As a proof of principle for the applicability of the new framework, we apply it to quantify human behavior in a sequential investment task. We find that the risk-sensitive variant provides a significantly better fit to the behavioral data and that it leads to an interpretation of the subject's responses that is indeed consistent with prospect theory. The analysis of simultaneously measured fMRI signals shows a significant correlation of the risk-sensitive TD error with BOLD signal change in the ventral striatum. In addition we find a significant correlation of the risk-sensitive Q-values with neural activity in the striatum, cingulate cortex, and insula that is not present if standard Q-values are used.

Apprenticeship Learning: Learning to Schedule from Human Experts

DTIC Science & Technology

2016-06-09

approaches to learning such models are based on Markov models, such as reinforcement learning or inverse reinforcement learning (Busoniu, Babuska, and De...via inverse reinforcement learning. In ICML. Barto, A. G., and Mahadevan, S. 2003. Recent advances in hierarchical reinforcement learning. Discrete...of tasks with temporal constraints. In Proc. AAAI, 2110–2116. Odom, P., and Natarajan, S. 2015. Active advice seeking for inverse reinforcement

Taste-immunosuppression engram: reinforcement and extinction.

PubMed

Niemi, Maj-Britt; Härting, Margarete; Kou, Wei; Del Rey, Adriana; Besedovsky, Hugo O; Schedlowski, Manfred; Pacheco-López, Gustavo

2007-08-01

Several Pavlovian conditioning paradigms have documented the brain's abilities to sense immune-derived signals or immune status, associate them with concurrently relevant extereoceptive stimuli, and reinstate such immune responses on demand. Specifically, the naturalistic relation of food ingestion with its possible immune consequences facilitates taste-immune associations. Here we demonstrate that the saccharin taste can be associated with the immunosuppressive agent cyclosporine A, and that such taste-immune associative learning is subject to reinforcement. Furthermore, once consolidated, this saccharin-immunosuppression engram is resistant to extinction when avoidance behavior is assessed. More importantly, the more this engram is activated, either at association or extinction phases, the more pronounced is the conditioned immunosuppression.

Lessons Learned from Autonomous Sciencecraft Experiment

NASA Technical Reports Server (NTRS)

Chien, Steve A.; Sherwood, Rob; Tran, Daniel; Cichy, Benjamin; Rabideau, Gregg; Castano, Rebecca; Davies, Ashley; Mandl, Dan; Frye, Stuart; Trout, Bruce;

Multi-Instance Learning Models for Automated Support of Analysts in Simulated Surveillance Environments

NASA Technical Reports Server (NTRS)

Birisan, Mihnea; Beling, Peter

2011-01-01

New generations of surveillance drones are being outfitted with numerous high definition cameras. The rapid proliferation of fielded sensors and supporting capacity for processing and displaying data will translate into ever more capable platforms, but with increased capability comes increased complexity and scale that may diminish the usefulness of such platforms to human operators. We investigate methods for alleviating strain on analysts by automatically retrieving content specific to their current task using a machine learning technique known as Multi-Instance Learning (MIL). We use MIL to create a real time model of the analysts' task and subsequently use the model to dynamically retrieve relevant content. This paper presents results from a pilot experiment in which a computer agent is assigned analyst tasks such as identifying caravanning vehicles in a simulated vehicle traffic environment. We compare agent performance between MIL aided trials and unaided trials.

Note-Taking within MetaTutor: Interactions between an Intelligent Tutoring System and Prior Knowledge on Note-Taking and Learning

ERIC Educational Resources Information Center

Trevors, Gregory; Duffy, Melissa; Azevedo, Roger

2014-01-01

Hypermedia learning environments (HLE) unevenly present new challenges and opportunities to learning processes and outcomes depending on learner characteristics and instructional supports. In this experimental study, we examined how one such HLE--MetaTutor, an intelligent, multi-agent tutoring system designed to scaffold cognitive and…

A graph-based evolutionary algorithm: Genetic Network Programming (GNP) and its extension using reinforcement learning.

PubMed

Mabu, Shingo; Hirasawa, Kotaro; Hu, Jinglu

2007-01-01

This paper proposes a graph-based evolutionary algorithm called Genetic Network Programming (GNP). Our goal is to develop GNP, which can deal with dynamic environments efficiently and effectively, based on the distinguished expression ability of the graph (network) structure. The characteristics of GNP are as follows. 1) GNP programs are composed of a number of nodes which execute simple judgment/processing, and these nodes are connected by directed links to each other. 2) The graph structure enables GNP to re-use nodes, thus the structure can be very compact. 3) The node transition of GNP is executed according to its node connections without any terminal nodes, thus the past history of the node transition affects the current node to be used and this characteristic works as an implicit memory function. These structural characteristics are useful for dealing with dynamic environments. Furthermore, we propose an extended algorithm, "GNP with Reinforcement Learning (GNPRL)" which combines evolution and reinforcement learning in order to create effective graph structures and obtain better results in dynamic environments. In this paper, we applied GNP to the problem of determining agents' behavior to evaluate its effectiveness. Tileworld was used as the simulation environment. The results show some advantages for GNP over conventional methods.

Using reinforcement learning to examine dynamic attention allocation during reading.

PubMed

Liu, Yanping; Reichle, Erik D; Gao, Ding-Guo

2013-01-01

A fundamental question in reading research concerns whether attention is allocated strictly serially, supporting lexical processing of one word at a time, or in parallel, supporting concurrent lexical processing of two or more words (Reichle, Liversedge, Pollatsek, & Rayner, 2009). The origins of this debate are reviewed. We then report three simulations to address this question using artificial reading agents (Liu & Reichle, 2010; Reichle & Laurent, 2006) that learn to dynamically allocate attention to 1-4 words to "read" as efficiently as possible. These simulation results indicate that the agents strongly preferred serial word processing, although they occasionally attended to more than one word concurrently. The reason for this preference is discussed, along with implications for the debate about how humans allocate attention during reading. Copyright © 2013 Cognitive Science Society, Inc.

Goal-directed EEG activity evoked by discriminative stimuli in reinforcement learning.

PubMed

Luque, David; Morís, Joaquín; Rushby, Jacqueline A; Le Pelley, Mike E

2015-02-01

In reinforcement learning (RL), discriminative stimuli (S) allow agents to anticipate the value of a future outcome, and the response that will produce that outcome. We examined this processing by recording EEG locked to S during RL. Incentive value of outcomes and predictive value of S were manipulated, allowing us to discriminate between outcome-related and response-related activity. S predicting the correct response differed from nonpredictive S in the P2. S paired with high-value outcomes differed from those paired with low-value outcomes in a frontocentral positivity and in the P3b. A slow negativity then distinguished between predictive and nonpredictive S. These results suggest that, first, attention prioritizes detection of informative S. Activation of mental representations of these informative S then retrieves representations of outcomes, which in turn retrieve representations of responses that previously produced those outcomes. © 2014 Society for Psychophysiological Research.

Interacting with an artificial partner: modeling the role of emotional aspects.

PubMed

Cattinelli, Isabella; Goldwurm, Massimiliano; Borghese, N Alberto

2008-12-01

In this paper we introduce a simple model based on probabilistic finite state automata to describe an emotional interaction between a robot and a human user, or between simulated agents. Based on the agent's personality, attitude, and nature, and on the emotional inputs it receives, the model will determine the next emotional state displayed by the agent itself. The probabilistic and time-varying nature of the model yields rich and dynamic interactions, and an autonomous adaptation to the interlocutor. In addition, a reinforcement learning technique is applied to have one agent drive its partner's behavior toward desired states. The model may also be used as a tool for behavior analysis, by extracting high probability patterns of interaction and by resorting to the ergodic properties of Markov chains.

Detection and Learning of Unexpected Behaviors of Systems of Dynamical Systems by Using the Q2 Abstractions

DTIC Science & Technology

2017-11-01

Finite State Machine ............................................... 21 9 Main Ontological Concepts for Representing Structure of a Multi -Agent...19 NetLogo Simulation of persistent surveillance of circular plume by 4 UAVs ........................36 20 Flocking Emergent Behaviors in Multi -UAV...Region) - Undesirable Group Formation ................................................................................... 40 24 Two UAVs Moving in

Hierarchical Reinforcement in Continuous State and Multi-Agent Environments

DTIC Science & Technology

2005-09-01

Mahadevan, Chair Andrew G. Barto, Member Victor R . Lesser, Member Weibo Gong, Member W. Bruce Croft, Department Chair Computer Science To my parents...of my cubicle during my unwanted one-year absence. Thank you Colin Barringer , Jad Davis, Andy Fagg, Jeffrey Johns, Anders Jonsson, George Konidaris...transforma- tions of the problem. One definition is that an MDP model M consists of five elements 〈S,A,P , R , I〉 defined as follows:1 • S: is the set of

A Framework System for Intelligent Support in Open Distributed Learning Environments--A Look Back from 16 Years Later

ERIC Educational Resources Information Center

Hoppe, H. Ulrich

2016-01-01

The 1998 paper by Martin Mühlenbrock, Frank Tewissen, and myself introduced a multi-agent architecture and a component engineering approach for building open distributed learning environments to support group learning in different types of classroom settings. It took up prior work on "multiple student modeling" as a method to configure…

Dynamic Educational e-Content Selection Using Multiple Criteria in Web-Based Personalized Learning Environments.

ERIC Educational Resources Information Center

Manouselis, Nikos; Sampson, Demetrios

This paper focuses on the way a multi-criteria decision making methodology is applied in the case of agent-based selection of offered learning objects. The problem of selection is modeled as a decision making one, with the decision variables being the learner model and the learning objects' educational description. In this way, selection of…

Exploiting Multi-Step Sample Trajectories for Approximate Value Iteration

DTIC Science & Technology

2013-09-01

WORK UNIT NUMBER IH 7. PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES) AFRL/ RISC 525 Brooks Road, Rome NY 13441-4505 Binghamton University...S) AND ADDRESS(ES) Air Force Research Laboratory/Information Directorate Rome Research Site/ RISC 525 Brooks Road Rome NY 13441-4505 10. SPONSOR...iteration methods for reinforcement learning (RL) generalize experience from limited samples across large state-action spaces. The function approximators

Unbiased and unnoticed verbal conditioning: the double agent robot procedure1

PubMed Central

Rosenfeld, Howard M.; Baer, Donald M.

1970-01-01

Subjects who were told they were “experimenters” attempted to reinforce fluent speech in a supposed subject with whom they spoke via intercom. The supposed subject was to say nouns, one at a time, on request by the “experimenter”, who reinforced fluent pronunciation with points. Actually, the “experimenter” was talking to a multi-track tape recording, one track of which contained fluently spoken nouns, the other track containing disfluently spoken nouns. If the “experimenter's” request for the next noun was in a specified form a word from the fluent track was played to him as reinforcement; requests in any other form produced the word from the disfluent track. Repeated conditioning of specific forms of requests was accomplished with two subject-“experimenters,” who were unable to describe changes in their own behavior, or the contingencies applied. This technique improved upon an earlier method that had yielded similar results, but was less thoroughly controlled against possible human bias. PMID:16811461

Adaptive Critic-based Neurofuzzy Controller for the Steam Generator Water Level

NASA Astrophysics Data System (ADS)

Fakhrazari, Amin; Boroushaki, Mehrdad

2008-06-01

In this paper, an adaptive critic-based neurofuzzy controller is presented for water level regulation of nuclear steam generators. The problem has been of great concern for many years as the steam generator is a highly nonlinear system showing inverse response dynamics especially at low operating power levels. Fuzzy critic-based learning is a reinforcement learning method based on dynamic programming. The only information available for the critic agent is the system feedback which is interpreted as the last action the controller has performed in the previous state. The signal produced by the critic agent is used alongside the backpropagation of error algorithm to tune online conclusion parts of the fuzzy inference rules. The critic agent here has a proportional-derivative structure and the fuzzy rule base has nine rules. The proposed controller shows satisfactory transient responses, disturbance rejection and robustness to model uncertainty. Its simple design procedure and structure, nominates it as one of the suitable controller designs for the steam generator water level control in nuclear power plant industry.

Team Formation in Partially Observable Multi-Agent Systems

NASA Technical Reports Server (NTRS)

Agogino, Adrian K.; Tumer, Kagan

2004-01-01

Sets of multi-agent teams often need to maximize a global utility rating the performance of the entire system where a team cannot fully observe other teams agents. Such limited observability hinders team-members trying to pursue their team utilities to take actions that also help maximize the global utility. In this article, we show how team utilities can be used in partially observable systems. Furthermore, we show how team sizes can be manipulated to provide the best compromise between having easy to learn team utilities and having them aligned with the global utility, The results show that optimally sized teams in a partially observable environments outperform one team in a fully observable environment, by up to 30%.

Rational and Mechanistic Perspectives on Reinforcement Learning

ERIC Educational Resources Information Center

Chater, Nick

2009-01-01

This special issue describes important recent developments in applying reinforcement learning models to capture neural and cognitive function. But reinforcement learning, as a theoretical framework, can apply at two very different levels of description: "mechanistic" and "rational." Reinforcement learning is often viewed in mechanistic terms--as…

Agent-Centric Approach for Cybersecurity Decision-Support with Partial Observability

DOE Office of Scientific and Technical Information (OSTI.GOV)

Tipireddy, Ramakrishna; Chatterjee, Samrat; Paulson, Patrick R.

Generating automated cyber resilience policies for real-world settings is a challenging research problem that must account for uncertainties in system state over time and dynamics between attackers and defenders. In addition to understanding attacker and defender motives and tools, and identifying “relevant” system and attack data, it is also critical to develop rigorous mathematical formulations representing the defender’s decision-support problem under uncertainty. Game-theoretic approaches involving cyber resource allocation optimization with Markov decision processes (MDP) have been previously proposed in the literature. Moreover, advancements in reinforcement learning approaches have motivated the development of partially observable stochastic games (POSGs) in various multi-agentmore » problem domains with partial information. Recent advances in cyber-system state space modeling have also generated interest in potential applicability of POSGs for cybersecurity. However, as is the case in strategic card games such as poker, research challenges using game-theoretic approaches for practical cyber defense applications include: 1) solving for equilibrium and designing efficient algorithms for large-scale, general problems; 2) establishing mathematical guarantees that equilibrium exists; 3) handling possible existence of multiple equilibria; and 4) exploitation of opponent weaknesses. Inspired by advances in solving strategic card games while acknowledging practical challenges associated with the use of game-theoretic approaches in cyber settings, this paper proposes an agent-centric approach for cybersecurity decision-support with partial system state observability.« less

Optimization through satisficing with prospects

NASA Astrophysics Data System (ADS)

Oyo, Kuratomo; Takahashi, Tatsuji

2017-07-01

As the broadening scope of reinforcement learning calls for a rational and more efficient heuristics, we test a satisficing strategy named RS, based on the theory of bounded rationality that considers the limited resources in agents. In K-armed bandit problems, despite its simpler form than the previous formalization of satisficing, RS shows better-than-optimal performances when the optimal aspiration level is given. We also show that RS shows a scalability for the number of actions, K, and an adaptability in the face of an infinite number of actions. It may be an efficient means for online learning in a complex or real environments.

A multi-agent intelligent environment for medical knowledge.

PubMed

Vicari, Rosa M; Flores, Cecilia D; Silvestre, André M; Seixas, Louise J; Ladeira, Marcelo; Coelho, Helder

2003-03-01

AMPLIA is a multi-agent intelligent learning environment designed to support training of diagnostic reasoning and modelling of domains with complex and uncertain knowledge. AMPLIA focuses on the medical area. It is a system that deals with uncertainty under the Bayesian network approach, where learner-modelling tasks will consist of creating a Bayesian network for a problem the system will present. The construction of a network involves qualitative and quantitative aspects. The qualitative part concerns the network topology, that is, causal relations among the domain variables. After it is ready, the quantitative part is specified. It is composed of the distribution of conditional probability of the variables represented. A negotiation process (managed by an intelligent MediatorAgent) will treat the differences of topology and probability distribution between the model the learner built and the one built-in in the system. That negotiation process occurs between the agents that represent the expert knowledge domain (DomainAgent) and the agent that represents the learner knowledge (LearnerAgent).

A Distributed Multi-Agent System for Collaborative Information Management and Learning

NASA Technical Reports Server (NTRS)

Chen, James R.; Wolfe, Shawn R.; Wragg, Stephen D.; Koga, Dennis (Technical Monitor)

2000-01-01

In this paper, we present DIAMS, a system of distributed, collaborative agents to help users access, manage, share and exchange information. A DIAMS personal agent helps its owner find information most relevant to current needs. It provides tools and utilities for users to manage their information repositories with dynamic organization and virtual views. Flexible hierarchical display is integrated with indexed query search-to support effective information access. Automatic indexing methods are employed to support user queries and communication between agents. Contents of a repository are kept in object-oriented storage to facilitate information sharing. Collaboration between users is aided by easy sharing utilities as well as automated information exchange. Matchmaker agents are designed to establish connections between users with similar interests and expertise. DIAMS agents provide needed services for users to share and learn information from one another on the World Wide Web.

Negative reinforcement learning is affected in substance dependence.

PubMed

Thompson, Laetitia L; Claus, Eric D; Mikulich-Gilbertson, Susan K; Banich, Marie T; Crowley, Thomas; Krmpotich, Theodore; Miller, David; Tanabe, Jody

2012-06-01

Negative reinforcement results in behavior to escape or avoid an aversive outcome. Withdrawal symptoms are purported to be negative reinforcers in perpetuating substance dependence, but little is known about negative reinforcement learning in this population. The purpose of this study was to examine reinforcement learning in substance dependent individuals (SDI), with an emphasis on assessing negative reinforcement learning. We modified the Iowa Gambling Task to separately assess positive and negative reinforcement. We hypothesized that SDI would show differences in negative reinforcement learning compared to controls and we investigated whether learning differed as a function of the relative magnitude or frequency of the reinforcer. Thirty subjects dependent on psychostimulants were compared with 28 community controls on a decision making task that manipulated outcome frequencies and magnitudes and required an action to avoid a negative outcome. SDI did not learn to avoid negative outcomes to the same degree as controls. This difference was driven by the magnitude, not the frequency, of negative feedback. In contrast, approach behaviors in response to positive reinforcement were similar in both groups. Our findings are consistent with a specific deficit in negative reinforcement learning in SDI. SDI were relatively insensitive to the magnitude, not frequency, of loss. If this generalizes to drug-related stimuli, it suggests that repeated episodes of withdrawal may drive relapse more than the severity of a single episode. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

An Upside to Reward Sensitivity: The Hippocampus Supports Enhanced Reinforcement Learning in Adolescence.

PubMed

Davidow, Juliet Y; Foerde, Karin; Galván, Adriana; Shohamy, Daphna

2016-10-05

Adolescents are notorious for engaging in reward-seeking behaviors, a tendency attributed to heightened activity in the brain's reward systems during adolescence. It has been suggested that reward sensitivity in adolescence might be adaptive, but evidence of an adaptive role has been scarce. Using a probabilistic reinforcement learning task combined with reinforcement learning models and fMRI, we found that adolescents showed better reinforcement learning and a stronger link between reinforcement learning and episodic memory for rewarding outcomes. This behavioral benefit was related to heightened prediction error-related BOLD activity in the hippocampus and to stronger functional connectivity between the hippocampus and the striatum at the time of reinforcement. These findings reveal an important role for the hippocampus in reinforcement learning in adolescence and suggest that reward sensitivity in adolescence is related to adaptive differences in how adolescents learn from experience. Copyright © 2016 Elsevier Inc. All rights reserved.

Studies on Multi Wall Carbon Nanotubes Reinforced Poly (trimethylene Terephthalate) Nanocomposite

NASA Astrophysics Data System (ADS)

Gupta, Anju; Manocha, L. M.; Choudhory, V.

2008-08-01

Poly (trimethylene terephthalate) (PTT) nanocomposites with multi walled carbon nanotubes (MWCNTs) have been prepared by a simple melt compounding using DMS microcompounder. The non-isothermal melt crystallization behavior of PTT in the presence of varying amounts of MWCNTs was investigated using DSC technique. An increase in crystallization temperature was observed upon incorporation of 0.1% MWCNTs thus indicating that CNTs act as nucleating agents. Percentage crystallinity as determined by WAXD also showed an increase upon incorporation of small amounts (0.5% w/w) of CNTs. The electrical conductivity of nanocomposites increased upon incorporation of MWCNTs and percolation was obtained at a loading in the range of 1-2% (w/w). Morphological characterization by SEM showed a uniform distribution of MWCNTs in PTT matrix.

Learning relative values in the striatum induces violations of normative decision making

PubMed Central

Klein, Tilmann A.; Ullsperger, Markus; Jocham, Gerhard

2017-01-01

To decide optimally between available options, organisms need to learn the values associated with these options. Reinforcement learning models offer a powerful explanation of how these values are learnt from experience. However, human choices often violate normative principles. We suggest that seemingly counterintuitive decisions may arise as a natural consequence of the learning mechanisms deployed by humans. Here, using fMRI and a novel behavioural task, we show that, when suddenly switched to novel choice contexts, participants’ choices are incongruent with values learnt by standard learning algorithms. Instead, behaviour is compatible with the decisions of an agent learning how good an option is relative to an option with which it had previously been paired. Striatal activity exhibits the characteristics of a prediction error used to update such relative option values. Our data suggest that choices can be biased by a tendency to learn option values with reference to the available alternatives. PMID:28631734

Future applications of artificial intelligence to Mission Control Centers

NASA Technical Reports Server (NTRS)

Friedland, Peter

1991-01-01

Future applications of artificial intelligence to Mission Control Centers are presented in the form of the viewgraphs. The following subject areas are covered: basic objectives of the NASA-wide AI program; inhouse research program; constraint-based scheduling; learning and performance improvement for scheduling; GEMPLAN multi-agent planner; planning, scheduling, and control; Bayesian learning; efficient learning algorithms; ICARUS (an integrated architecture for learning); design knowledge acquisition and retention; computer-integrated documentation; and some speculation on future applications.

A game theoretic framework for incentive-based models of intrinsic motivation in artificial systems

PubMed Central

Merrick, Kathryn E.; Shafi, Kamran

2013-01-01

An emerging body of research is focusing on understanding and building artificial systems that can achieve open-ended development influenced by intrinsic motivations. In particular, research in robotics and machine learning is yielding systems and algorithms with increasing capacity for self-directed learning and autonomy. Traditional software architectures and algorithms are being augmented with intrinsic motivations to drive cumulative acquisition of knowledge and skills. Intrinsic motivations have recently been considered in reinforcement learning, active learning and supervised learning settings among others. This paper considers game theory as a novel setting for intrinsic motivation. A game theoretic framework for intrinsic motivation is formulated by introducing the concept of optimally motivating incentive as a lens through which players perceive a game. Transformations of four well-known mixed-motive games are presented to demonstrate the perceived games when players' optimally motivating incentive falls in three cases corresponding to strong power, affiliation and achievement motivation. We use agent-based simulations to demonstrate that players with different optimally motivating incentive act differently as a result of their altered perception of the game. We discuss the implications of these results both for modeling human behavior and for designing artificial agents or robots. PMID:24198797

A game theoretic framework for incentive-based models of intrinsic motivation in artificial systems.

PubMed

Merrick, Kathryn E; Shafi, Kamran

2013-01-01

An emerging body of research is focusing on understanding and building artificial systems that can achieve open-ended development influenced by intrinsic motivations. In particular, research in robotics and machine learning is yielding systems and algorithms with increasing capacity for self-directed learning and autonomy. Traditional software architectures and algorithms are being augmented with intrinsic motivations to drive cumulative acquisition of knowledge and skills. Intrinsic motivations have recently been considered in reinforcement learning, active learning and supervised learning settings among others. This paper considers game theory as a novel setting for intrinsic motivation. A game theoretic framework for intrinsic motivation is formulated by introducing the concept of optimally motivating incentive as a lens through which players perceive a game. Transformations of four well-known mixed-motive games are presented to demonstrate the perceived games when players' optimally motivating incentive falls in three cases corresponding to strong power, affiliation and achievement motivation. We use agent-based simulations to demonstrate that players with different optimally motivating incentive act differently as a result of their altered perception of the game. We discuss the implications of these results both for modeling human behavior and for designing artificial agents or robots.

Efficient Agent-Based Models for Non-Genomic Evolution

NASA Technical Reports Server (NTRS)

Gupta, Nachi; Agogino, Adrian; Tumer, Kagan

2006-01-01

Modeling dynamical systems composed of aggregations of primitive proteins is critical to the field of astrobiological science involving early evolutionary structures and the origins of life. Unfortunately traditional non-multi-agent methods either require oversimplified models or are slow to converge to adequate solutions. This paper shows how to address these deficiencies by modeling the protein aggregations through a utility based multi-agent system. In this method each agent controls the properties of a set of proteins assigned to that agent. Some of these properties determine the dynamics of the system, such as the ability for some proteins to join or split other proteins, while additional properties determine the aggregation s fitness as a viable primitive cell. We show that over a wide range of starting conditions, there are mechanisins that allow protein aggregations to achieve high values of overall fitness. In addition through the use of agent-specific utilities that remain aligned with the overall global utility, we are able to reach these conclusions with 50 times fewer learning steps.

Benchmarking for Bayesian Reinforcement Learning

PubMed Central

Ernst, Damien; Couëtoux, Adrien

2016-01-01

In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the collected rewards while interacting with their environment while using some prior knowledge that is accessed beforehand. Many BRL algorithms have already been proposed, but the benchmarks used to compare them are only relevant for specific cases. The paper addresses this problem, and provides a new BRL comparison methodology along with the corresponding open source library. In this methodology, a comparison criterion that measures the performance of algorithms on large sets of Markov Decision Processes (MDPs) drawn from some probability distributions is defined. In order to enable the comparison of non-anytime algorithms, our methodology also includes a detailed analysis of the computation time requirement of each algorithm. Our library is released with all source code and documentation: it includes three test problems, each of which has two different prior distributions, and seven state-of-the-art RL algorithms. Finally, our library is illustrated by comparing all the available algorithms and the results are discussed. PMID:27304891

Benchmarking for Bayesian Reinforcement Learning.

PubMed

Castronovo, Michael; Ernst, Damien; Couëtoux, Adrien; Fonteneau, Raphael

2016-01-01

In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the collected rewards while interacting with their environment while using some prior knowledge that is accessed beforehand. Many BRL algorithms have already been proposed, but the benchmarks used to compare them are only relevant for specific cases. The paper addresses this problem, and provides a new BRL comparison methodology along with the corresponding open source library. In this methodology, a comparison criterion that measures the performance of algorithms on large sets of Markov Decision Processes (MDPs) drawn from some probability distributions is defined. In order to enable the comparison of non-anytime algorithms, our methodology also includes a detailed analysis of the computation time requirement of each algorithm. Our library is released with all source code and documentation: it includes three test problems, each of which has two different prior distributions, and seven state-of-the-art RL algorithms. Finally, our library is illustrated by comparing all the available algorithms and the results are discussed.

Roles of OA1 octopamine receptor and Dop1 dopamine receptor in mediating appetitive and aversive reinforcement revealed by RNAi studies

PubMed Central

Awata, Hiroko; Wakuda, Ryo; Ishimaru, Yoshiyasu; Matsuoka, Yuji; Terao, Kanta; Katata, Satomi; Matsumoto, Yukihisa; Hamanaka, Yoshitaka; Noji, Sumihare; Mito, Taro; Mizunami, Makoto

2016-01-01

Revealing reinforcing mechanisms in associative learning is important for elucidation of brain mechanisms of behavior. In mammals, dopamine neurons are thought to mediate both appetitive and aversive reinforcement signals. Studies using transgenic fruit-flies suggested that dopamine neurons mediate both appetitive and aversive reinforcements, through the Dop1 dopamine receptor, but our studies using octopamine and dopamine receptor antagonists and using Dop1 knockout crickets suggested that octopamine neurons mediate appetitive reinforcement and dopamine neurons mediate aversive reinforcement in associative learning in crickets. To fully resolve this issue, we examined the effects of silencing of expression of genes that code the OA1 octopamine receptor and Dop1 and Dop2 dopamine receptors by RNAi in crickets. OA1-silenced crickets exhibited impairment in appetitive learning with water but not in aversive learning with sodium chloride solution, while Dop1-silenced crickets exhibited impairment in aversive learning but not in appetitive learning. Dop2-silenced crickets showed normal scores in both appetitive learning and aversive learning. The results indicate that octopamine neurons mediate appetitive reinforcement via OA1 and that dopamine neurons mediate aversive reinforcement via Dop1 in crickets, providing decisive evidence that neurotransmitters and receptors that mediate appetitive reinforcement indeed differ among different species of insects. PMID:27412401

Roles of OA1 octopamine receptor and Dop1 dopamine receptor in mediating appetitive and aversive reinforcement revealed by RNAi studies.

PubMed

Awata, Hiroko; Wakuda, Ryo; Ishimaru, Yoshiyasu; Matsuoka, Yuji; Terao, Kanta; Katata, Satomi; Matsumoto, Yukihisa; Hamanaka, Yoshitaka; Noji, Sumihare; Mito, Taro; Mizunami, Makoto

2016-07-14

Revealing reinforcing mechanisms in associative learning is important for elucidation of brain mechanisms of behavior. In mammals, dopamine neurons are thought to mediate both appetitive and aversive reinforcement signals. Studies using transgenic fruit-flies suggested that dopamine neurons mediate both appetitive and aversive reinforcements, through the Dop1 dopamine receptor, but our studies using octopamine and dopamine receptor antagonists and using Dop1 knockout crickets suggested that octopamine neurons mediate appetitive reinforcement and dopamine neurons mediate aversive reinforcement in associative learning in crickets. To fully resolve this issue, we examined the effects of silencing of expression of genes that code the OA1 octopamine receptor and Dop1 and Dop2 dopamine receptors by RNAi in crickets. OA1-silenced crickets exhibited impairment in appetitive learning with water but not in aversive learning with sodium chloride solution, while Dop1-silenced crickets exhibited impairment in aversive learning but not in appetitive learning. Dop2-silenced crickets showed normal scores in both appetitive learning and aversive learning. The results indicate that octopamine neurons mediate appetitive reinforcement via OA1 and that dopamine neurons mediate aversive reinforcement via Dop1 in crickets, providing decisive evidence that neurotransmitters and receptors that mediate appetitive reinforcement indeed differ among different species of insects.

Multi-Length Scale-Enriched Continuum-Level Material Model for Kevlar-Fiber-Reinforced Polymer-Matrix Composites

DTIC Science & Technology

2012-08-03

is unlimited. Multi-Length Scale-Enriched Continuum-Level Material Model for Kevlar ®-Fiber-Reinforced Polymer-Matrix Composites The views, opinions...12211 Research Triangle Park, NC 27709-2211 ballistics, composites, Kevlar , material models, microstructural defects REPORT DOCUMENTATION PAGE 11... Kevlar ®-Fiber-Reinforced Polymer-Matrix Composites Report Title Fiber-reinforced polymer matrix composite materials display quite complex deformation

Longitudinal investigation on learned helplessness tested under negative and positive reinforcement involving stimulus control.

PubMed

Oliveira, Emileane C; Hunziker, Maria Helena

2014-07-01

In this study, we investigated whether (a) animals demonstrating the learned helplessness effect during an escape contingency also show learning deficits under positive reinforcement contingencies involving stimulus control and (b) the exposure to positive reinforcement contingencies eliminates the learned helplessness effect under an escape contingency. Rats were initially exposed to controllable (C), uncontrollable (U) or no (N) shocks. After 24h, they were exposed to 60 escapable shocks delivered in a shuttlebox. In the following phase, we selected from each group the four subjects that presented the most typical group pattern: no escape learning (learned helplessness effect) in Group U and escape learning in Groups C and N. All subjects were then exposed to two phases, the (1) positive reinforcement for lever pressing under a multiple FR/Extinction schedule and (2) a re-test under negative reinforcement (escape). A fourth group (n=4) was exposed only to the positive reinforcement sessions. All subjects showed discrimination learning under multiple schedule. In the escape re-test, the learned helplessness effect was maintained for three of the animals in Group U. These results suggest that the learned helplessness effect did not extend to discriminative behavior that is positively reinforced and that the learned helplessness effect did not revert for most subjects after exposure to positive reinforcement. We discuss some theoretical implications as related to learned helplessness as an effect restricted to aversive contingencies and to the absence of reversion after positive reinforcement. This article is part of a Special Issue entitled: insert SI title. Copyright © 2014. Published by Elsevier B.V.

An approximate dynamic programming approach to resource management in multi-cloud scenarios

NASA Astrophysics Data System (ADS)

Pietrabissa, Antonio; Priscoli, Francesco Delli; Di Giorgio, Alessandro; Giuseppi, Alessandro; Panfili, Martina; Suraci, Vincenzo

2017-03-01

The programmability and the virtualisation of network resources are crucial to deploy scalable Information and Communications Technology (ICT) services. The increasing demand of cloud services, mainly devoted to the storage and computing, requires a new functional element, the Cloud Management Broker (CMB), aimed at managing multiple cloud resources to meet the customers' requirements and, simultaneously, to optimise their usage. This paper proposes a multi-cloud resource allocation algorithm that manages the resource requests with the aim of maximising the CMB revenue over time. The algorithm is based on Markov decision process modelling and relies on reinforcement learning techniques to find online an approximate solution.

Stress affects instrumental learning based on positive or negative reinforcement in interaction with personality in domestic horses

PubMed Central

Valenchon, Mathilde; Lévy, Frédéric; Moussu, Chantal; Lansade, Léa

2017-01-01

The present study investigated how stress affects instrumental learning performance in horses (Equus caballus) depending on the type of reinforcement. Horses were assigned to four groups (N = 15 per group); each group received training with negative or positive reinforcement in the presence or absence of stressors unrelated to the learning task. The instrumental learning task consisted of the horse entering one of two compartments at the appearance of a visual signal given by the experimenter. In the absence of stressors unrelated to the task, learning performance did not differ between negative and positive reinforcements. The presence of stressors unrelated to the task (exposure to novel and sudden stimuli) impaired learning performance. Interestingly, this learning deficit was smaller when the negative reinforcement was used. The negative reinforcement, considered as a stressor related to the task, could have counterbalanced the impact of the extrinsic stressor by focusing attention toward the learning task. In addition, learning performance appears to differ between certain dimensions of personality depending on the presence of stressors and the type of reinforcement. These results suggest that when negative reinforcement is used (i.e. stressor related to the task), the most fearful horses may be the best performers in the absence of stressors but the worst performers when stressors are present. On the contrary, when positive reinforcement is used, the most fearful horses appear to be consistently the worst performers, with and without exposure to stressors unrelated to the learning task. This study is the first to demonstrate in ungulates that stress affects learning performance differentially according to the type of reinforcement and in interaction with personality. It provides fundamental and applied perspectives in the understanding of the relationships between personality and training abilities. PMID:28475581

Fiber-Reinforced Epoxy Composites and Methods of Making Same Without the Use of Oven or Autoclave

NASA Technical Reports Server (NTRS)

Barnell, Thomas J. (Inventor); Rauscher, Michael D. (Inventor); Stienecker, Rick D. (Inventor); Nickerson, David M. (Inventor); Tong, Tat H. (Inventor)

2016-01-01

Method embodiments for producing a fiber-reinforced epoxy composite comprise providing a mold defining a shape for a composite, applying a fiber reinforcement over the mold, covering the mold and fiber reinforcement thereon in a vacuum enclosure, performing a vacuum on the vacuum enclosure to produce a pressure gradient, insulating at least a portion of the vacuum enclosure with thermal insulation, infusing the fiber reinforcement with a reactive mixture of uncured epoxy resin and curing agent under vacuum conditions, wherein the reactive mixture of uncured epoxy resin and curing agent generates exothermic heat, and producing the fiber-reinforced epoxy composite having a glass transition temperature of at least about 100.degree. C. by curing the fiber reinforcement infused with the reactive mixture of uncured epoxy resin and curing agent by utilizing the exothermically generated heat, wherein the curing is conducted inside the thermally insulated vacuum enclosure without utilization of an external heat source or an external radiation source.

Multi-Agent Inference in Social Networks: A Finite Population Learning Approach.

PubMed

Fan, Jianqing; Tong, Xin; Zeng, Yao

When people in a society want to make inference about some parameter, each person may want to use data collected by other people. Information (data) exchange in social networks is usually costly, so to make reliable statistical decisions, people need to trade off the benefits and costs of information acquisition. Conflicts of interests and coordination problems will arise in the process. Classical statistics does not consider people's incentives and interactions in the data collection process. To address this imperfection, this work explores multi-agent Bayesian inference problems with a game theoretic social network model. Motivated by our interest in aggregate inference at the societal level, we propose a new concept, finite population learning , to address whether with high probability, a large fraction of people in a given finite population network can make "good" inference. Serving as a foundation, this concept enables us to study the long run trend of aggregate inference quality as population grows.

Self-organization in a distributed coordination game through heuristic rules

NASA Astrophysics Data System (ADS)

Agarwal, Shubham; Ghosh, Diptesh; Chakrabarti, Anindya S.

2016-12-01

In this paper, we consider a distributed coordination game played by a large number of agents with finite information sets, which characterizes emergence of a single dominant attribute out of a large number of competitors. Formally, N agents play a coordination game repeatedly, which has exactly N pure strategy Nash equilibria, and all of the equilibria are equally preferred by the agents. The problem is to select one equilibrium out of N possible equilibria in the least number of attempts. We propose a number of heuristic rules based on reinforcement learning to solve the coordination problem. We see that the agents self-organize into clusters with varying intensities depending on the heuristic rule applied, although all clusters but one are transitory in most cases. Finally, we characterize a trade-off in terms of the time requirement to achieve a degree of stability in strategies versus the efficiency of such a solution.

In search of intelligence: evolving a developmental neuron capable of learning

NASA Astrophysics Data System (ADS)

Khan, Gul Muhammad; Miller, Julian Francis

2014-10-01

A neuro-inspired multi-chromosomal genotype for a single developmental neuron capable of learning and developing memory is proposed. This genotype is evolved so that the phenotype which changes and develops during an agent's lifetime (while problem-solving) gives the agent the capacity for learning by experience. Seven important processes of signal processing and neural structure development are identified from biology and encoded using Cartesian Genetic Programming. These chromosomes represent the electrical and developmental aspects of dendrites, axonal branches, synapses and the neuron soma. The neural morphology that occurs by running these chromosomes is highly dynamic. The dendritic/axonal branches and synaptic connections form and change in response to situations encountered in the learning task. The approach has been evaluated in the context of maze-solving and the board game of checkers (draughts) demonstrating interesting learning capabilities. The motivation underlying this research is to, ab initio, evolve genotypes that build phenotypes with an ability to learn.

Racial bias shapes social reinforcement learning.

PubMed

Lindström, Björn; Selbing, Ida; Molapour, Tanaz; Olsson, Andreas

2014-03-01

Both emotional facial expressions and markers of racial-group belonging are ubiquitous signals in social interaction, but little is known about how these signals together affect future behavior through learning. To address this issue, we investigated how emotional (threatening or friendly) in-group and out-group faces reinforced behavior in a reinforcement-learning task. We asked whether reinforcement learning would be modulated by intergroup attitudes (i.e., racial bias). The results showed that individual differences in racial bias critically modulated reinforcement learning. As predicted, racial bias was associated with more efficiently learned avoidance of threatening out-group individuals. We used computational modeling analysis to quantitatively delimit the underlying processes affected by social reinforcement. These analyses showed that racial bias modulates the rate at which exposure to threatening out-group individuals is transformed into future avoidance behavior. In concert, these results shed new light on the learning processes underlying social interaction with racial-in-group and out-group individuals.

Toward cognitive robotics

NASA Astrophysics Data System (ADS)

Laird, John E.

2009-05-01

Our long-term goal is to develop autonomous robotic systems that have the cognitive abilities of humans, including communication, coordination, adapting to novel situations, and learning through experience. Our approach rests on the recent integration of the Soar cognitive architecture with both virtual and physical robotic systems. Soar has been used to develop a wide variety of knowledge-rich agents for complex virtual environments, including distributed training environments and interactive computer games. For development and testing in robotic virtual environments, Soar interfaces to a variety of robotic simulators and a simple mobile robot. We have recently made significant extensions to Soar that add new memories and new non-symbolic reasoning to Soar's original symbolic processing, which should significantly improve Soar abilities for control of robots. These extensions include episodic memory, semantic memory, reinforcement learning, and mental imagery. Episodic memory and semantic memory support the learning and recalling of prior events and situations as well as facts about the world. Reinforcement learning provides the ability of the system to tune its procedural knowledge - knowledge about how to do things. Mental imagery supports the use of diagrammatic and visual representations that are critical to support spatial reasoning. We speculate on the future of unmanned systems and the need for cognitive robotics to support dynamic instruction and taskability.

Discounting of reward sequences: a test of competing formal models of hyperbolic discounting

PubMed Central

Zarr, Noah; Alexander, William H.; Brown, Joshua W.

2014-01-01

Humans are known to discount future rewards hyperbolically in time. Nevertheless, a formal recursive model of hyperbolic discounting has been elusive until recently, with the introduction of the hyperbolically discounted temporal difference (HDTD) model. Prior to that, models of learning (especially reinforcement learning) have relied on exponential discounting, which generally provides poorer fits to behavioral data. Recently, it has been shown that hyperbolic discounting can also be approximated by a summed distribution of exponentially discounted values, instantiated in the μAgents model. The HDTD model and the μAgents model differ in one key respect, namely how they treat sequences of rewards. The μAgents model is a particular implementation of a Parallel discounting model, which values sequences based on the summed value of the individual rewards whereas the HDTD model contains a non-linear interaction. To discriminate among these models, we observed how subjects discounted a sequence of three rewards, and then we tested how well each candidate model fit the subject data. The results show that the Parallel model generally provides a better fit to the human data. PMID:24639662

Navigating complex decision spaces: Problems and paradigms in sequential choice

PubMed Central

Walsh, Matthew M.; Anderson, John R.

2015-01-01

To behave adaptively, we must learn from the consequences of our actions. Doing so is difficult when the consequences of an action follow a delay. This introduces the problem of temporal credit assignment. When feedback follows a sequence of decisions, how should the individual assign credit to the intermediate actions that comprise the sequence? Research in reinforcement learning provides two general solutions to this problem: model-free reinforcement learning and model-based reinforcement learning. In this review, we examine connections between stimulus-response and cognitive learning theories, habitual and goal-directed control, and model-free and model-based reinforcement learning. We then consider a range of problems related to temporal credit assignment. These include second-order conditioning and secondary reinforcers, latent learning and detour behavior, partially observable Markov decision processes, actions with distributed outcomes, and hierarchical learning. We ask whether humans and animals, when faced with these problems, behave in a manner consistent with reinforcement learning techniques. Throughout, we seek to identify neural substrates of model-free and model-based reinforcement learning. The former class of techniques is understood in terms of the neurotransmitter dopamine and its effects in the basal ganglia. The latter is understood in terms of a distributed network of regions including the prefrontal cortex, medial temporal lobes cerebellum, and basal ganglia. Not only do reinforcement learning techniques have a natural interpretation in terms of human and animal behavior, but they also provide a useful framework for understanding neural reward valuation and action selection. PMID:23834192

Model-Based Reinforcement Learning under Concurrent Schedules of Reinforcement in Rodents

ERIC Educational Resources Information Center

Huh, Namjung; Jo, Suhyun; Kim, Hoseok; Sul, Jung Hoon; Jung, Min Whan

2009-01-01

Reinforcement learning theories postulate that actions are chosen to maximize a long-term sum of positive outcomes based on value functions, which are subjective estimates of future rewards. In simple reinforcement learning algorithms, value functions are updated only by trial-and-error, whereas they are updated according to the decision-maker's…

Prediction error and trace dominance determine the fate of fear memories after post-training manipulations

PubMed Central

Alfei, Joaquín M.; Ferrer Monti, Roque I.; Molina, Victor A.; Bueno, Adrián M.

2015-01-01

Different mnemonic outcomes have been observed when associative memories are reactivated by CS exposure and followed by amnestics. These outcomes include mere retrieval, destabilization–reconsolidation, a transitional period (which is insensitive to amnestics), and extinction learning. However, little is known about the interaction between initial learning conditions and these outcomes during a reinforced or nonreinforced reactivation. Here we systematically combined temporally specific memories with different reactivation parameters to observe whether these four outcomes are determined by the conditions established during training. First, we validated two training regimens with different temporal expectations about US arrival. Then, using Midazolam (MDZ) as an amnestic agent, fear memories in both learning conditions were submitted to retraining either under identical or different parameters to the original training. Destabilization (i.e., susceptibly to MDZ) occurred when reactivation was reinforced, provided the occurrence of a temporal prediction error about US arrival. In subsequent experiments, both treatments were systematically reactivated by nonreinforced context exposure of different lengths, which allowed to explore the interaction between training and reactivation lengths. These results suggest that temporal prediction error and trace dominance determine the extent to which reactivation produces the different outcomes. PMID:26179232

Emergence of distributed coordination in the Kolkata Paise Restaurant problem with finite information

NASA Astrophysics Data System (ADS)

Ghosh, Diptesh; Chakrabarti, Anindya S.

2017-10-01

In this paper, we study a large-scale distributed coordination problem and propose efficient adaptive strategies to solve the problem. The basic problem is to allocate finite number of resources to individual agents in the absence of a central planner such that there is as little congestion as possible and the fraction of unutilized resources is reduced as far as possible. In the absence of a central planner and global information, agents can employ adaptive strategies that uses only a finite knowledge about the competitors. In this paper, we show that a combination of finite information sets and reinforcement learning can increase the utilization fraction of resources substantially.

GA-based fuzzy reinforcement learning for control of a magnetic bearing system.

PubMed

Lin, C T; Jou, C P

2000-01-01

This paper proposes a TD (temporal difference) and GA (genetic algorithm)-based reinforcement (TDGAR) learning method and applies it to the control of a real magnetic bearing system. The TDGAR learning scheme is a new hybrid GA, which integrates the TD prediction method and the GA to perform the reinforcement learning task. The TDGAR learning system is composed of two integrated feedforward networks. One neural network acts as a critic network to guide the learning of the other network (the action network) which determines the outputs (actions) of the TDGAR learning system. The action network can be a normal neural network or a neural fuzzy network. Using the TD prediction method, the critic network can predict the external reinforcement signal and provide a more informative internal reinforcement signal to the action network. The action network uses the GA to adapt itself according to the internal reinforcement signal. The key concept of the TDGAR learning scheme is to formulate the internal reinforcement signal as the fitness function for the GA such that the GA can evaluate the candidate solutions (chromosomes) regularly, even during periods without external feedback from the environment. This enables the GA to proceed to new generations regularly without waiting for the arrival of the external reinforcement signal. This can usually accelerate the GA learning since a reinforcement signal may only be available at a time long after a sequence of actions has occurred in the reinforcement learning problem. The proposed TDGAR learning system has been used to control an active magnetic bearing (AMB) system in practice. A systematic design procedure is developed to achieve successful integration of all the subsystems including magnetic suspension, mechanical structure, and controller training. The results show that the TDGAR learning scheme can successfully find a neural controller or a neural fuzzy controller for a self-designed magnetic bearing system.

Grounding the Meanings in Sensorimotor Behavior using Reinforcement Learning

PubMed Central

Farkaš, Igor; Malík, Tomáš; Rebrová, Kristína

2012-01-01

The recent outburst of interest in cognitive developmental robotics is fueled by the ambition to propose ecologically plausible mechanisms of how, among other things, a learning agent/robot could ground linguistic meanings in its sensorimotor behavior. Along this stream, we propose a model that allows the simulated iCub robot to learn the meanings of actions (point, touch, and push) oriented toward objects in robot’s peripersonal space. In our experiments, the iCub learns to execute motor actions and comment on them. Architecturally, the model is composed of three neural-network-based modules that are trained in different ways. The first module, a two-layer perceptron, is trained by back-propagation to attend to the target position in the visual scene, given the low-level visual information and the feature-based target information. The second module, having the form of an actor-critic architecture, is the most distinguishing part of our model, and is trained by a continuous version of reinforcement learning to execute actions as sequences, based on a linguistic command. The third module, an echo-state network, is trained to provide the linguistic description of the executed actions. The trained model generalizes well in case of novel action-target combinations with randomized initial arm positions. It can also promptly adapt its behavior if the action/target suddenly changes during motor execution. PMID:22393319

A comparison of plan-based and abstract MDP reward shaping

NASA Astrophysics Data System (ADS)

Efthymiadis, Kyriakos; Kudenko, Daniel

2014-01-01

Reward shaping has been shown to significantly improve an agent's performance in reinforcement learning. As attention is shifting away from tabula-rasa approaches many different reward shaping methods have been developed. In this paper, we compare two different methods for reward shaping; plan-based, in which an agent is provided with a plan and extra rewards are given according to the steps of the plan the agent satisfies, and reward shaping via abstract Markov decision process (MDPs), in which an abstract high-level MDP of the environment is solved and the resulting value function is used to shape the agent. The comparison is conducted in terms of total reward, convergence speed and scaling up to more complex environments. Empirical results demonstrate the need to correctly select and set up reward shaping methods according to the needs of the environment the agents are acting in. This leads to the more interesting question, is there a reward shaping method which is universally better than all other approaches regardless of the environment dynamics?

11.2 YIP Human In the Loop Statistical RelationalLearners

DTIC Science & Technology

2017-10-23

learning formalisms including inverse reinforcement learning [4] and statistical relational learning [7, 5, 8]. We have also applied our algorithms in...one introduced for label preferences. 4 Figure 2: Active Advice Seeking for Inverse Reinforcement Learning. active advice seeking is in selecting the...learning tasks. 1.2.1 Sequential Decision-Making Our previous work on advice for inverse reinforcement learning (IRL) defined advice as action

Coordinating Learning Agents for Active Information Collection

DTIC Science & Technology

2011-06-30

the experiments were not particularly sensitive to this parameter. By limiting the number of actions that are updated (DANT-L in black/ dark ), the...Bazzan, A. and Ossowski, S. (eds.), Applications of Agent Technology in Traffic and Transportation (Springer, 2005). [19] Mataric , M. J., Coordination...organizing market (1998), preprint cond- mat/9802177. [19] Jones, C. and Mataric , M. J., Adaptive division of labor in large-scale multi-robot systems, in IEEE

Characterization of MWCNT/Nanoclay Binary Nanoparticles Modified Composites and Fatigue Performance Evaluation of Nanoclay Modified Fiber Reinforced Composites

DTIC Science & Technology

2014-04-21

modified with binary nanoparticles consist of multi-walled carbon nanotubes (MWCNTs) and nanoclays together. First, epoxy SC-15 resin was reinforced...modified with binary nanoparticles consist of multi-walled carbon nanotubes (MWCNTs) and nanoclays together. First, epoxy SC-15 resin was reinforced with...7 2.2.1 Carbon Nanotube

Effects of dopamine on reinforcement learning and consolidation in Parkinson's disease.

PubMed

Grogan, John P; Tsivos, Demitra; Smith, Laura; Knight, Brogan E; Bogacz, Rafal; Whone, Alan; Coulthard, Elizabeth J

2017-07-10

Emerging evidence suggests that dopamine may modulate learning and memory with important implications for understanding the neurobiology of memory and future therapeutic targeting. An influential hypothesis posits that dopamine biases reinforcement learning. More recent data also suggest an influence during both consolidation and retrieval. Eighteen Parkinson's disease patients learned through feedback ON or OFF medication, with memory tested 24 hr later ON or OFF medication (4 conditions, within-subjects design with matched healthy control group). Patients OFF medication during learning decreased in memory accuracy over the following 24 hr. In contrast to previous studies, however, dopaminergic medication during learning and testing did not affect expression of positive or negative reinforcement. Two further experiments were run without the 24 hr delay, but they too failed to reproduce effects of dopaminergic medication on reinforcement learning. While supportive of a dopaminergic role in consolidation, this study failed to replicate previous findings on reinforcement learning.

Enhanced Experience Replay for Deep Reinforcement Learning

DTIC Science & Technology

2015-11-01

ARL-TR-7538 ● NOV 2015 US Army Research Laboratory Enhanced Experience Replay for Deep Reinforcement Learning by David Doria...Experience Replay for Deep Reinforcement Learning by David Doria, Bryan Dawson, and Manuel Vindiola Computational and Information Sciences Directorate...

A Q-Learning Approach to Flocking With UAVs in a Stochastic Environment.

PubMed

Hung, Shao-Ming; Givigi, Sidney N

2017-01-01

In the past two decades, unmanned aerial vehicles (UAVs) have demonstrated their efficacy in supporting both military and civilian applications, where tasks can be dull, dirty, dangerous, or simply too costly with conventional methods. Many of the applications contain tasks that can be executed in parallel, hence the natural progression is to deploy multiple UAVs working together as a force multiplier. However, to do so requires autonomous coordination among the UAVs, similar to swarming behaviors seen in animals and insects. This paper looks at flocking with small fixed-wing UAVs in the context of a model-free reinforcement learning problem. In particular, Peng's Q(λ) with a variable learning rate is employed by the followers to learn a control policy that facilitates flocking in a leader-follower topology. The problem is structured as a Markov decision process, where the agents are modeled as small fixed-wing UAVs that experience stochasticity due to disturbances such as winds and control noises, as well as weight and balance issues. Learned policies are compared to ones solved using stochastic optimal control (i.e., dynamic programming) by evaluating the average cost incurred during flight according to a cost function. Simulation results demonstrate the feasibility of the proposed learning approach at enabling agents to learn how to flock in a leader-follower topology, while operating in a nonstationary stochastic environment.

Trust-based learning and behaviors for convoy obstacle avoidance

NASA Astrophysics Data System (ADS)

Mikulski, Dariusz G.; Karlsen, Robert E.

2015-05-01

In many multi-agent systems, robots within the same team are regarded as being fully trustworthy for cooperative tasks. However, the assumption of trustworthiness is not always justified, which may not only increase the risk of mission failure, but also endanger the lives of friendly forces. In prior work, we addressed this issue by using RoboTrust to dynamically adjust to observed behaviors or recommendations in order to mitigate the risks of illegitimate behaviors. However, in the simulations in prior work, all members of the convoy had knowledge of the convoy goal. In this paper, only the lead vehicle has knowledge of the convoy goals and the follow vehicles must infer trustworthiness strictly from lead vehicle performance. In addition, RoboTrust could only respond to observed performance and did not dynamically learn agent behavior. In this paper, we incorporate an adaptive agent-specific bias into the RoboTrust algorithm that modifies its trust dynamics. This bias is learned incrementally from agent interactions, allowing good agents to benefit from faster trust growth and slower trust decay and bad agents to be penalized with slower trust growth and faster trust decay. We then integrate this new trust model into a trust-based controller for decentralized autonomous convoy operations. We evaluate its performance in an obstacle avoidance mission, where the convoy attempts to learn the best speed and following distances combinations for an acceptable obstacle avoidance probability.

Prespeech motor learning in a neural network using reinforcement.

PubMed

Warlaumont, Anne S; Westermann, Gert; Buder, Eugene H; Oller, D Kimbrough

2013-02-01

Vocal motor development in infancy provides a crucial foundation for language development. Some significant early accomplishments include learning to control the process of phonation (the production of sound at the larynx) and learning to produce the sounds of one's language. Previous work has shown that social reinforcement shapes the kinds of vocalizations infants produce. We present a neural network model that provides an account of how vocal learning may be guided by reinforcement. The model consists of a self-organizing map that outputs to muscles of a realistic vocalization synthesizer. Vocalizations are spontaneously produced by the network. If a vocalization meets certain acoustic criteria, it is reinforced, and the weights are updated to make similar muscle activations increasingly likely to recur. We ran simulations of the model under various reinforcement criteria and tested the types of vocalizations it produced after learning in the different conditions. When reinforcement was contingent on the production of phonated (i.e. voiced) sounds, the network's post-learning productions were almost always phonated, whereas when reinforcement was not contingent on phonation, the network's post-learning productions were almost always not phonated. When reinforcement was contingent on both phonation and proximity to English vowels as opposed to Korean vowels, the model's post-learning productions were more likely to resemble the English vowels and vice versa. Copyright © 2012 Elsevier Ltd. All rights reserved.

Reconciling Reinforcement Learning Models with Behavioral Extinction and Renewal: Implications for Addiction, Relapse, and Problem Gambling

ERIC Educational Resources Information Center

Redish, A. David; Jensen, Steve; Johnson, Adam; Kurth-Nelson, Zeb

2007-01-01

Because learned associations are quickly renewed following extinction, the extinction process must include processes other than unlearning. However, reinforcement learning models, such as the temporal difference reinforcement learning (TDRL) model, treat extinction as an unlearning of associated value and are thus unable to capture renewal. TDRL…

Behavioral and neural properties of social reinforcement learning

PubMed Central

Jones, Rebecca M.; Somerville, Leah H.; Li, Jian; Ruberry, Erika J.; Libby, Victoria; Glover, Gary; Voss, Henning U.; Ballon, Douglas J.; Casey, BJ

2011-01-01

Social learning is critical for engaging in complex interactions with other individuals. Learning from positive social exchanges, such as acceptance from peers, may be similar to basic reinforcement learning. We formally test this hypothesis by developing a novel paradigm that is based upon work in non-human primates and human imaging studies of reinforcement learning. The probability of receiving positive social reinforcement from three distinct peers was parametrically manipulated while brain activity was recorded in healthy adults using event-related functional magnetic resonance imaging (fMRI). Over the course of the experiment, participants responded more quickly to faces of peers who provided more frequent positive social reinforcement, and rated them as more likeable. Modeling trial-by-trial learning showed ventral striatum and orbital frontal cortex activity correlated positively with forming expectations about receiving social reinforcement. Rostral anterior cingulate cortex activity tracked positively with modulations of expected value of the cues (peers). Together, the findings across three levels of analysis - social preferences, response latencies and modeling neural responses – are consistent with reinforcement learning theory and non-human primate electrophysiological studies of reward. This work highlights the fundamental influence of acceptance by one’s peers in altering subsequent behavior. PMID:21917787

Classroom-based and distance learning education and training courses in end-of-life care for health and social care staff: a systematic review.

PubMed

Pulsford, David; Jackson, Georgina; O'Brien, Terri; Yates, Sue; Duxbury, Joy

2013-03-01

Staff from a range of health and social care professions report deficits in their knowledge and skills when providing end-of-life and palliative care, and education and training has been advocated at a range of levels. To review the literature related to classroom-based and distance learning education and training initiatives for health and social care staff in end-of-life and palliative care, in terms of their target audience, extent, modes of delivery, content and teaching and learning strategies, and to identify the most effective educational strategies for enhancing care. A systematic review of the literature evaluating classroom-based and distance learning education and training courses for health and social care staff in end-of-life and palliative care. Online databases CINAHL, MEDLINE, EMBASE and PSYCHINFO between January 2000 and July 2010. Studies were selected that discussed specific education and training initiatives and included pre-and post-test evaluation of participants' learning. 30 studies met eligibility criteria. The majority reported successful outcomes, though there were some exceptions. Level of prior experience and availability of practice reinforcement influenced learning. Participative and interactive learning strategies were predominantly used along with discussion of case scenarios. Multi-professional learning was infrequently reported and service user and carer input to curriculum development and delivery was reported in only one study. Classroom-based education and training is useful for enhancing professionals' skills and perceived preparedness for delivering end-of-life care but should be reinforced by actual practice experience.

A Cognitive Game Theoretic Analysis of Conflict Alerts in Air Traffic Control

NASA Technical Reports Server (NTRS)

Erev, Ido; Gopher, Daniel; Remington, Roger

1999-01-01

The current research was motivated by the recommendation made by a joint Government/Industry committee to introduce a new traffic control system, referred to as the Free Flight. This system is designed to use recent new technology to facilitate efficient and safe air transportation. We addressed one of the major difficulties that arise in the design of this and similar multi-agent systems: the adaptive (and slippery) nature of human agents. To facilitate a safe and efficient design of this multi-agent system, designers have to rely on assessments of the expected behavior of the different agents under various scenarios. Whereas the behavior of the computerized agents is predictable, the behavior of the human agents (including air traffic controllers and pilots) is not. Experimental and empirical observations suggest that human agents are likely to adjust their behavior to the design of the system. To see the difficulty that the adaptive nature of human agents creates assume that a good approximation of the way operators currently behave is available. Given this information an optimal design can be performed. The problem arises as the human operator will learn to adjust their behavior to the new system. Following this adjustment process the assumptions made by the designer concerning the operators behavior will no longer be accurate and the system might reach a suboptimal state. In extreme situations these potential suboptimal states might involve unnecessary risk. That is, the fact that operators learn in an adaptive fashion does not imply that the system will become safer as they gain experience. At least in the context of Safety dilemmas, experience can lead to a pareto deficient risk taking behavior.

The combination of appetitive and aversive reinforcers and the nature of their interaction during auditory learning.

PubMed

Ilango, A; Wetzel, W; Scheich, H; Ohl, F W

2010-03-31

Learned changes in behavior can be elicited by either appetitive or aversive reinforcers. It is, however, not clear whether the two types of motivation, (approaching appetitive stimuli and avoiding aversive stimuli) drive learning in the same or different ways, nor is their interaction understood in situations where the two types are combined in a single experiment. To investigate this question we have developed a novel learning paradigm for Mongolian gerbils, which not only allows rewards and punishments to be presented in isolation or in combination with each other, but also can use these opposite reinforcers to drive the same learned behavior. Specifically, we studied learning of tone-conditioned hurdle crossing in a shuttle box driven by either an appetitive reinforcer (brain stimulation reward) or an aversive reinforcer (electrical footshock), or by a combination of both. Combination of the two reinforcers potentiated speed of acquisition, led to maximum possible performance, and delayed extinction as compared to either reinforcer alone. Additional experiments, using partial reinforcement protocols and experiments in which one of the reinforcers was omitted after the animals had been previously trained with the combination of both reinforcers, indicated that appetitive and aversive reinforcers operated together but acted in different ways: in this particular experimental context, punishment appeared to be more effective for initial acquisition and reward more effective to maintain a high level of conditioned responses (CRs). The results imply that learning mechanisms in problem solving were maximally effective when the initial punishment of mistakes was combined with the subsequent rewarding of correct performance. Copyright 2010 IBRO. Published by Elsevier Ltd. All rights reserved.

Punishment Insensitivity and Impaired Reinforcement Learning in Preschoolers

ERIC Educational Resources Information Center

Briggs-Gowan, Margaret J.; Nichols, Sara R.; Voss, Joel; Zobel, Elvira; Carter, Alice S.; McCarthy, Kimberly J.; Pine, Daniel S.; Blair, James; Wakschlag, Lauren S.

2014-01-01

Background: Youth and adults with psychopathic traits display disrupted reinforcement learning. Advances in measurement now enable examination of this association in preschoolers. The current study examines relations between reinforcement learning in preschoolers and parent ratings of reduced responsiveness to socialization, conceptualized as a…

Agent Collaborative Target Localization and Classification in Wireless Sensor Networks

PubMed Central

Wang, Xue; Bi, Dao-wei; Ding, Liang; Wang, Sheng

2007-01-01

Wireless sensor networks (WSNs) are autonomous networks that have been frequently deployed to collaboratively perform target localization and classification tasks. Their autonomous and collaborative features resemble the characteristics of agents. Such similarities inspire the development of heterogeneous agent architecture for WSN in this paper. The proposed agent architecture views WSN as multi-agent systems and mobile agents are employed to reduce in-network communication. According to the architecture, an energy based acoustic localization algorithm is proposed. In localization, estimate of target location is obtained by steepest descent search. The search algorithm adapts to measurement environments by dynamically adjusting its termination condition. With the agent architecture, target classification is accomplished by distributed support vector machine (SVM). Mobile agents are employed for feature extraction and distributed SVM learning to reduce communication load. Desirable learning performance is guaranteed by combining support vectors and convex hull vectors. Fusion algorithms are designed to merge SVM classification decisions made from various modalities. Real world experiments with MICAz sensor nodes are conducted for vehicle localization and classification. Experimental results show the proposed agent architecture remarkably facilitates WSN designs and algorithm implementation. The localization and classification algorithms also prove to be accurate and energy efficient.

Neural signatures of trust in reciprocity: a coordinate-based meta-analysis

PubMed Central

Bellucci, Gabriele; Chernyak, Sergey V.; Goodyear, Kimberly; Eickhoff, Simon B.; Krueger, Frank

2017-01-01

Trust in reciprocity (TR) is defined as the risky decision to invest valued resources in another party with the hope of mutual benefit. Several fMRI studies have investigated the neural correlates of TR in one-shot and multi-round versions of the investment game (IG). However, an overall characterization of the underlying neural networks remains elusive. Here, we employed a coordinate-based meta-analysis (activation likelihood estimation method, 30 papers) to investigate consistent brain activations in each of the IG stages (i.e., the trust, reciprocity and feedback stage). Our results showed consistent activations in the anterior insula (AI) during trust decisions in the one-shot IG and decisions to reciprocate in the multi-round IG, likely related to representations of aversive feelings. Moreover, decisions to reciprocate also consistently engaged the intraparietal sulcus, probably involved in evaluations of the reciprocity options. On the contrary, trust decisions in the multi-round IG consistently activated the ventral striatum, likely associated with reward prediction error signals. Finally, the dorsal striatum was found consistently recruited during the feedback stage of the multi-round IG, likely related to reinforcement learning. In conclusion, our results indicate different neural networks underlying trust, reciprocity and feedback learning. These findings suggest that although decisions to trust and reciprocate may elicit aversive feelings likely evoked by the uncertainty about the decision outcomes and the pressing requirements of social standards, multiple interactions allow people to build interpersonal trust for cooperation via a learning mechanism by which they arguably learn to distinguish trustworthy from untrustworthy partners. PMID:27859899

Risk-Seeking Versus Risk-Avoiding Investments in Noisy Periodic Environments

NASA Astrophysics Data System (ADS)

Navarro-Barrientos, J. Emeterio; Walter, Frank E.; Schweitzer, Frank

We study the performance of various agent strategies in an artificial investment scenario. Agents are equipped with a budget, x(t), and at each time step invest a particular fraction, q(t), of their budget. The return on investment (RoI), r(t), is characterized by a periodic function with different types and levels of noise. Risk-avoiding agents choose their fraction q(t) proportional to the expected positive RoI, while risk-seeking agents always choose a maximum value qmax if they predict the RoI to be positive ("everything on red"). In addition to these different strategies, agents have different capabilities to predict the future r(t), dependent on their internal complexity. Here, we compare "zero-intelligent" agents using technical analysis (such as moving least squares) with agents using reinforcement learning or genetic algorithms to predict r(t). The performance of agents is measured by their average budget growth after a certain number of time steps. We present results of extensive computer simulations, which show that, for our given artificial environment, (i) the risk-seeking strategy outperforms the risk-avoiding one, and (ii) the genetic algorithm was able to find this optimal strategy itself, and thus outperforms other prediction approaches considered.

Distributed learning and multi-objectivity in traffic light control

NASA Astrophysics Data System (ADS)

Brys, Tim; Pham, Tong T.; Taylor, Matthew E.

2014-01-01

Traffic jams and suboptimal traffic flows are ubiquitous in modern societies, and they create enormous economic losses each year. Delays at traffic lights alone account for roughly 10% of all delays in US traffic. As most traffic light scheduling systems currently in use are static, set up by human experts rather than being adaptive, the interest in machine learning approaches to this problem has increased in recent years. Reinforcement learning (RL) approaches are often used in these studies, as they require little pre-existing knowledge about traffic flows. Distributed constraint optimisation approaches (DCOP) have also been shown to be successful, but are limited to cases where the traffic flows are known. The distributed coordination of exploration and exploitation (DCEE) framework was recently proposed to introduce learning in the DCOP framework. In this paper, we present a study of DCEE and RL techniques in a complex simulator, illustrating the particular advantages of each, comparing them against standard isolated traffic actuated signals. We analyse how learning and coordination behave under different traffic conditions, and discuss the multi-objective nature of the problem. Finally we evaluate several alternative reward signals in the best performing approach, some of these taking advantage of the correlation between the problem-inherent objectives to improve performance.

The role of GABAB receptors in human reinforcement learning.

PubMed

Ort, Andres; Kometer, Michael; Rohde, Judith; Seifritz, Erich; Vollenweider, Franz X

2014-10-01

Behavioral evidence from human studies suggests that the γ-aminobutyric acid type B receptor (GABAB receptor) agonist baclofen modulates reinforcement learning and reduces craving in patients with addiction spectrum disorders. However, in contrast to the well established role of dopamine in reinforcement learning, the mechanisms by which the GABAB receptor influences reinforcement learning in humans remain completely unknown. To further elucidate this issue, a cross-over, double-blind, placebo-controlled study was performed in healthy human subjects (N=15) to test the effects of baclofen (20 and 50mg p.o.) on probabilistic reinforcement learning. Outcomes were the feedback-induced P2 component of the event-related potential, the feedback-related negativity, and the P300 component of the event-related potential. Baclofen produced a reduction of P2 amplitude over the course of the experiment, but did not modulate the feedback-related negativity. Furthermore, there was a trend towards increased learning after baclofen administration relative to placebo over the course of the experiment. The present results extend previous theories of reinforcement learning, which focus on the importance of mesolimbic dopamine signaling, and indicate that stimulation of cortical GABAB receptors in a fronto-parietal network leads to better attentional allocation in reinforcement learning. This observation is a first step in our understanding of how baclofen may improve reinforcement learning in healthy subjects. Further studies with bigger sample sizes are needed to corroborate this conclusion and furthermore, test this effect in patients with addiction spectrum disorder. Copyright © 2014 Elsevier B.V. and ECNP. All rights reserved.

Effects of dopamine on reinforcement learning and consolidation in Parkinson’s disease

PubMed Central

Grogan, John P; Tsivos, Demitra; Smith, Laura; Knight, Brogan E; Bogacz, Rafal; Whone, Alan; Coulthard, Elizabeth J

2017-01-01

Emerging evidence suggests that dopamine may modulate learning and memory with important implications for understanding the neurobiology of memory and future therapeutic targeting. An influential hypothesis posits that dopamine biases reinforcement learning. More recent data also suggest an influence during both consolidation and retrieval. Eighteen Parkinson’s disease patients learned through feedback ON or OFF medication, with memory tested 24 hr later ON or OFF medication (4 conditions, within-subjects design with matched healthy control group). Patients OFF medication during learning decreased in memory accuracy over the following 24 hr. In contrast to previous studies, however, dopaminergic medication during learning and testing did not affect expression of positive or negative reinforcement. Two further experiments were run without the 24 hr delay, but they too failed to reproduce effects of dopaminergic medication on reinforcement learning. While supportive of a dopaminergic role in consolidation, this study failed to replicate previous findings on reinforcement learning. DOI: http://dx.doi.org/10.7554/eLife.26801.001 PMID:28691905

Fear of losing money? Aversive conditioning with secondary reinforcers.

PubMed

Delgado, M R; Labouliere, C D; Phelps, E A

2006-12-01

Money is a secondary reinforcer that acquires its value through social communication and interaction. In everyday human behavior and laboratory studies, money has been shown to influence appetitive or reward learning. It is unclear, however, if money has a similar impact on aversive learning. The goal of this study was to investigate the efficacy of money in aversive learning, comparing it with primary reinforcers that are traditionally used in fear conditioning paradigms. A series of experiments were conducted in which participants initially played a gambling game that led to a monetary gain. They were then presented with an aversive conditioning paradigm, with either shock (primary reinforcer) or loss of money (secondary reinforcer) as the unconditioned stimulus. Skin conductance responses and subjective ratings indicated that potential monetary loss modulated the conditioned response. Depending on the presentation context, the secondary reinforcer was as effective as the primary reinforcer during aversive conditioning. These results suggest that stimuli that acquire reinforcing properties through social communication and interaction, such as money, can effectively influence aversive learning.

Reinforcement learning and Tourette syndrome.

PubMed

Palminteri, Stefano; Pessiglione, Mathias

2013-01-01

In this chapter, we report the first experimental explorations of reinforcement learning in Tourette syndrome, realized by our team in the last few years. This report will be preceded by an introduction aimed to provide the reader with the state of the art of the knowledge concerning the neural bases of reinforcement learning at the moment of these studies and the scientific rationale beyond them. In short, reinforcement learning is learning by trial and error to maximize rewards and minimize punishments. This decision-making and learning process implicates the dopaminergic system projecting to the frontal cortex-basal ganglia circuits. A large body of evidence suggests that the dysfunction of the same neural systems is implicated in the pathophysiology of Tourette syndrome. Our results show that Tourette condition, as well as the most common pharmacological treatments (dopamine antagonists), affects reinforcement learning performance in these patients. Specifically, the results suggest a deficit in negative reinforcement learning, possibly underpinned by a functional hyperdopaminergia, which could explain the persistence of tics, despite their evident inadaptive (negative) value. This idea, together with the implications of these results in Tourette therapy and the future perspectives, is discussed in Section 4 of this chapter. © 2013 Elsevier Inc. All rights reserved.

Multi-Agent Inference in Social Networks: A Finite Population Learning Approach

PubMed Central

Tong, Xin; Zeng, Yao

2016-01-01

When people in a society want to make inference about some parameter, each person may want to use data collected by other people. Information (data) exchange in social networks is usually costly, so to make reliable statistical decisions, people need to trade off the benefits and costs of information acquisition. Conflicts of interests and coordination problems will arise in the process. Classical statistics does not consider people’s incentives and interactions in the data collection process. To address this imperfection, this work explores multi-agent Bayesian inference problems with a game theoretic social network model. Motivated by our interest in aggregate inference at the societal level, we propose a new concept, finite population learning, to address whether with high probability, a large fraction of people in a given finite population network can make “good” inference. Serving as a foundation, this concept enables us to study the long run trend of aggregate inference quality as population grows. PMID:27076691

Neural Mechanism for Stochastic Behavior During a Competitive Game

PubMed Central

Soltani, Alireza; Lee, Daeyeol; Wang, Xiao-Jing

2006-01-01

Previous studies have shown that non-human primates can generate highly stochastic choice behavior, especially when this is required during a competitive interaction with another agent. To understand the neural mechanism of such dynamic choice behavior, we propose a biologically plausible model of decision making endowed with synaptic plasticity that follows a reward-dependent stochastic Hebbian learning rule. This model constitutes a biophysical implementation of reinforcement learning, and it reproduces salient features of behavioral data from an experiment with monkeys playing a matching pennies game. Due to interaction with an opponent and learning dynamics, the model generates quasi-random behavior robustly in spite of intrinsic biases. Furthermore, non-random choice behavior can also emerge when the model plays against a non-interactive opponent, as observed in the monkey experiment. Finally, when combined with a meta-learning algorithm, our model accounts for the slow drift in the animal’s strategy based on a process of reward maximization. PMID:17015181

Alterations in choice behavior by manipulations of world model.

PubMed

Green, C S; Benson, C; Kersten, D; Schrater, P

2010-09-14

How to compute initially unknown reward values makes up one of the key problems in reinforcement learning theory, with two basic approaches being used. Model-free algorithms rely on the accumulation of substantial amounts of experience to compute the value of actions, whereas in model-based learning, the agent seeks to learn the generative process for outcomes from which the value of actions can be predicted. Here we show that (i) "probability matching"-a consistent example of suboptimal choice behavior seen in humans-occurs in an optimal Bayesian model-based learner using a max decision rule that is initialized with ecologically plausible, but incorrect beliefs about the generative process for outcomes and (ii) human behavior can be strongly and predictably altered by the presence of cues suggestive of various generative processes, despite statistically identical outcome generation. These results suggest human decision making is rational and model based and not consistent with model-free learning.

Alterations in choice behavior by manipulations of world model

PubMed Central

Green, C. S.; Benson, C.; Kersten, D.; Schrater, P.

2010-01-01

How to compute initially unknown reward values makes up one of the key problems in reinforcement learning theory, with two basic approaches being used. Model-free algorithms rely on the accumulation of substantial amounts of experience to compute the value of actions, whereas in model-based learning, the agent seeks to learn the generative process for outcomes from which the value of actions can be predicted. Here we show that (i) “probability matching”—a consistent example of suboptimal choice behavior seen in humans—occurs in an optimal Bayesian model-based learner using a max decision rule that is initialized with ecologically plausible, but incorrect beliefs about the generative process for outcomes and (ii) human behavior can be strongly and predictably altered by the presence of cues suggestive of various generative processes, despite statistically identical outcome generation. These results suggest human decision making is rational and model based and not consistent with model-free learning. PMID:20805507

On the integration of reinforcement learning and approximate reasoning for control

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.

1991-01-01

The author discusses the importance of strengthening the knowledge representation characteristic of reinforcement learning techniques using methods such as approximate reasoning. The ARIC (approximate reasoning-based intelligent control) architecture is an example of such a hybrid approach in which the fuzzy control rules are modified (fine-tuned) using reinforcement learning. ARIC also demonstrates that it is possible to start with an approximately correct control knowledge base and learn to refine this knowledge through further experience. On the other hand, techniques such as the TD (temporal difference) algorithm and Q-learning establish stronger theoretical foundations for their use in adaptive control and also in stability analysis of hybrid reinforcement learning and approximate reasoning-based controllers.

Evaluation of Multi-Functional Materials for Deep Space Radiation Shielding

NASA Technical Reports Server (NTRS)

Rojdev, Kristina; Atwell, William; Wilkins, Richard; Gersey, Brad; Badavi, Francis F.

2009-01-01

Small scale trade study of materials for radiation shielding: a) High-hydrogen polymers; b) Z-graded materials; c) Fiber-reinforced polymer composites. Discussed multi-functionality of fiber-reinforced polymer composites. Preliminary results of ground testing data.

Multiagent Reinforcement Learning With Sparse Interactions by Negotiation and Knowledge Transfer.

PubMed

Zhou, Luowei; Yang, Pei; Chen, Chunlin; Gao, Yang

2017-05-01

Reinforcement learning has significant applications for multiagent systems, especially in unknown dynamic environments. However, most multiagent reinforcement learning (MARL) algorithms suffer from such problems as exponential computation complexity in the joint state-action space, which makes it difficult to scale up to realistic multiagent problems. In this paper, a novel algorithm named negotiation-based MARL with sparse interactions (NegoSIs) is presented. In contrast to traditional sparse-interaction-based MARL algorithms, NegoSI adopts the equilibrium concept and makes it possible for agents to select the nonstrict equilibrium-dominating strategy profile (nonstrict EDSP) or meta equilibrium for their joint actions. The presented NegoSI algorithm consists of four parts: 1) the equilibrium-based framework for sparse interactions; 2) the negotiation for the equilibrium set; 3) the minimum variance method for selecting one joint action; and 4) the knowledge transfer of local Q -values. In this integrated algorithm, three techniques, i.e., unshared value functions, equilibrium solutions, and sparse interactions are adopted to achieve privacy protection, better coordination and lower computational complexity, respectively. To evaluate the performance of the presented NegoSI algorithm, two groups of experiments are carried out regarding three criteria: 1) steps of each episode; 2) rewards of each episode; and 3) average runtime. The first group of experiments is conducted using six grid world games and shows fast convergence and high scalability of the presented algorithm. Then in the second group of experiments NegoSI is applied to an intelligent warehouse problem and simulated results demonstrate the effectiveness of the presented NegoSI algorithm compared with other state-of-the-art MARL algorithms.

Intelligence moderates reinforcement learning: a mini-review of the neural evidence

PubMed Central

2014-01-01

Our understanding of the neural basis of reinforcement learning and intelligence, two key factors contributing to human strivings, has progressed significantly recently. However, the overlap of these two lines of research, namely, how intelligence affects neural responses during reinforcement learning, remains uninvestigated. A mini-review of three existing studies suggests that higher IQ (especially fluid IQ) may enhance the neural signal of positive prediction error in dorsolateral prefrontal cortex, dorsal anterior cingulate cortex, and striatum, several brain substrates of reinforcement learning or intelligence. PMID:25185818

Intelligence moderates reinforcement learning: a mini-review of the neural evidence.

PubMed

Chen, Chong

2015-06-01

Our understanding of the neural basis of reinforcement learning and intelligence, two key factors contributing to human strivings, has progressed significantly recently. However, the overlap of these two lines of research, namely, how intelligence affects neural responses during reinforcement learning, remains uninvestigated. A mini-review of three existing studies suggests that higher IQ (especially fluid IQ) may enhance the neural signal of positive prediction error in dorsolateral prefrontal cortex, dorsal anterior cingulate cortex, and striatum, several brain substrates of reinforcement learning or intelligence. Copyright © 2015 the American Physiological Society.

Prespeech motor learning in a neural network using reinforcement☆

PubMed Central

Warlaumont, Anne S.; Westermann, Gert; Buder, Eugene H.; Oller, D. Kimbrough

2012-01-01

Vocal motor development in infancy provides a crucial foundation for language development. Some significant early accomplishments include learning to control the process of phonation (the production of sound at the larynx) and learning to produce the sounds of one’s language. Previous work has shown that social reinforcement shapes the kinds of vocalizations infants produce. We present a neural network model that provides an account of how vocal learning may be guided by reinforcement. The model consists of a self-organizing map that outputs to muscles of a realistic vocalization synthesizer. Vocalizations are spontaneously produced by the network. If a vocalization meets certain acoustic criteria, it is reinforced, and the weights are updated to make similar muscle activations increasingly likely to recur. We ran simulations of the model under various reinforcement criteria and tested the types of vocalizations it produced after learning in the differ-ent conditions. When reinforcement was contingent on the production of phonated (i.e. voiced) sounds, the network’s post learning productions were almost always phonated, whereas when reinforcement was not contingent on phonation, the network’s post-learning productions were almost always not phonated. When reinforcement was contingent on both phonation and proximity to English vowels as opposed to Korean vowels, the model’s post-learning productions were more likely to resemble the English vowels and vice versa. PMID:23275137

Reinforcement learning in complementarity game and population dynamics

NASA Astrophysics Data System (ADS)

Jost, Jürgen; Li, Wei

2014-02-01

We systematically test and compare different reinforcement learning schemes in a complementarity game [J. Jost and W. Li, Physica A 345, 245 (2005), 10.1016/j.physa.2004.07.005] played between members of two populations. More precisely, we study the Roth-Erev, Bush-Mosteller, and SoftMax reinforcement learning schemes. A modified version of Roth-Erev with a power exponent of 1.5, as opposed to 1 in the standard version, performs best. We also compare these reinforcement learning strategies with evolutionary schemes. This gives insight into aspects like the issue of quick adaptation as opposed to systematic exploration or the role of learning rates.

Fluid Structure Interaction Effects on Composites Under Low Velocity Impact

DTIC Science & Technology

2012-06-01

Nanotubes ( MWCNTs ) and the second had no reinforcements at the interface layer in front of the pre-cracks. Output from both tests was recorded using...these samples were tested. The first was reinforced with Multi-Walled Carbon Nanotubes ( MWCNTs ) and the second had no reinforcements at the interface...Ethyl Ketone Peroxide MWCNT Multi-Walled Carbon Nanotube VARTM Vacuum-Assisted Resin Transfer Molding xiv THIS PAGE INTENTIONALLY LEFT BLANK

The prefrontal cortex and hybrid learning during iterative competitive games.

PubMed

Abe, Hiroshi; Seo, Hyojung; Lee, Daeyeol

2011-12-01

Behavioral changes driven by reinforcement and punishment are referred to as simple or model-free reinforcement learning. Animals can also change their behaviors by observing events that are neither appetitive nor aversive when these events provide new information about payoffs available from alternative actions. This is an example of model-based reinforcement learning and can be accomplished by incorporating hypothetical reward signals into the value functions for specific actions. Recent neuroimaging and single-neuron recording studies showed that the prefrontal cortex and the striatum are involved not only in reinforcement and punishment, but also in model-based reinforcement learning. We found evidence for both types of learning, and hence hybrid learning, in monkeys during simulated competitive games. In addition, in both the dorsolateral prefrontal cortex and orbitofrontal cortex, individual neurons heterogeneously encoded signals related to actual and hypothetical outcomes from specific actions, suggesting that both areas might contribute to hybrid learning. © 2011 New York Academy of Sciences.

Knowledge-Directed Theory Revision

NASA Astrophysics Data System (ADS)

Ali, Kamal; Leung, Kevin; Konik, Tolga; Choi, Dongkyu; Shapiro, Dan

Using domain knowledge to speed up learning is widely accepted but theory revision of such knowledge continues to use general syntactic operators. Using such operators for theory revision of teleoreactive logic programs is especially expensive in which proof of a top-level goal involves playing a game. In such contexts, one should have the option to complement general theory revision with domain-specific knowledge. Using American football as an example, we use Icarus' multi-agent teleoreactive logic programming ability to encode a coach agent whose concepts correspond to faults recognized in execution of the play and whose skills correspond to making repairs in the goals of the player agents. Our results show effective learning using as few as twenty examples. We also show that structural changes made by such revision can produce performance gains that cannot be matched by doing only numeric optimization.

Nanotubular Toughening Inclusions

NASA Technical Reports Server (NTRS)

Park, Cheol (Inventor); Working, Dennis C. (Inventor); Siochi, Emilie J. (Inventor); Harrison, Joycelyn S. (Inventor)

2017-01-01

Conventional toughening agents are typically rubbery materials or small molecular weight molecules, which mostly sacrifice the intrinsic properties of a matrix such as modulus, strength, and thermal stability as side effects. On the other hand, high modulus inclusions tend to reinforce elastic modulus very efficiently, but not the strength very well. For example, mechanical reinforcement with inorganic inclusions often degrades the composite toughness, encountering a frequent catastrophic brittle failure triggered by minute chips and cracks. Thus, toughening generally conflicts with mechanical reinforcement. Carbon nanotubes have been used as efficient reinforcing agents in various applications due to their combination of extraordinary mechanical, electrical, and thermal properties. Moreover, nanotubes can elongate more than 20% without yielding or breaking, and absorb significant amounts of energy during deformation, which enables them to also be an efficient toughening agent, as well as excellent reinforcing inclusion. Accordingly, an improved toughening method is provided by incorporating nanotubular inclusions into a host matrix, such as thermoset and thermoplastic polymers or ceramics without detrimental effects on the intrinsic physical properties of the matrix.

Nanotubular Toughening Inclusions

NASA Technical Reports Server (NTRS)

Park, Cheol (Inventor); Working, Dennis C. (Inventor); Siochi, Emilie J. (Inventor); Harrison, Joycelyn S. (Inventor)

2015-01-01

Conventional toughening agents are typically rubbery materials or small molecular weight molecules, which mostly sacrifice the intrinsic properties of a matrix such as modulus, strength, and thermal stability as side effects. On the other hand, high modulus inclusions tend to reinforce elastic modulus very efficiently, but not the strength very well. For example, mechanical reinforcement with inorganic inclusions often degrades the composite toughness, encountering a frequent catastrophic brittle failure triggered by minute chips and cracks. Thus, toughening generally conflicts with mechanical reinforcement. Carbon nanotubes have been used as efficient reinforcing agents in various applications due to their combination of extraordinary mechanical, electrical, and thermal properties. Moreover, nanotubes can elongate more than 20% without yielding or breaking, and absorb significant amounts of energy during deformation, which enables them to also be an efficient toughening agent, as well as excellent reinforcing inclusion. Accordingly, an improved toughening method is provided by incorporating nanotubular inclusions into a host matrix, such as thermoset and thermoplastic polymers or ceramics without detrimental effects on the matrix's intrinsic physical properties.

Reinforcement Learning and Dopamine in Schizophrenia: Dimensions of Symptoms or Specific Features of a Disease Group?

PubMed Central

Deserno, Lorenz; Boehme, Rebecca; Heinz, Andreas; Schlagenhauf, Florian

2013-01-01

Abnormalities in reinforcement learning are a key finding in schizophrenia and have been proposed to be linked to elevated levels of dopamine neurotransmission. Behavioral deficits in reinforcement learning and their neural correlates may contribute to the formation of clinical characteristics of schizophrenia. The ability to form predictions about future outcomes is fundamental for environmental interactions and depends on neuronal teaching signals, like reward prediction errors. While aberrant prediction errors, that encode non-salient events as surprising, have been proposed to contribute to the formation of positive symptoms, a failure to build neural representations of decision values may result in negative symptoms. Here, we review behavioral and neuroimaging research in schizophrenia and focus on studies that implemented reinforcement learning models. In addition, we discuss studies that combined reinforcement learning with measures of dopamine. Thereby, we suggest how reinforcement learning abnormalities in schizophrenia may contribute to the formation of psychotic symptoms and may interact with cognitive deficits. These ideas point toward an interplay of more rigid versus flexible control over reinforcement learning. Pronounced deficits in the flexible or model-based domain may allow for a detailed characterization of well-established cognitive deficits in schizophrenia patients based on computational models of learning. Finally, we propose a framework based on the potentially crucial contribution of dopamine to dysfunctional reinforcement learning on the level of neural networks. Future research may strongly benefit from computational modeling but also requires further methodological improvement for clinical group studies. These research tools may help to improve our understanding of disease-specific mechanisms and may help to identify clinically relevant subgroups of the heterogeneous entity schizophrenia. PMID:24391603

Generalization of value in reinforcement learning by humans.

PubMed

Wimmer, G Elliott; Daw, Nathaniel D; Shohamy, Daphna

2012-04-01

Research in decision-making has focused on the role of dopamine and its striatal targets in guiding choices via learned stimulus-reward or stimulus-response associations, behavior that is well described by reinforcement learning theories. However, basic reinforcement learning is relatively limited in scope and does not explain how learning about stimulus regularities or relations may guide decision-making. A candidate mechanism for this type of learning comes from the domain of memory, which has highlighted a role for the hippocampus in learning of stimulus-stimulus relations, typically dissociated from the role of the striatum in stimulus-response learning. Here, we used functional magnetic resonance imaging and computational model-based analyses to examine the joint contributions of these mechanisms to reinforcement learning. Humans performed a reinforcement learning task with added relational structure, modeled after tasks used to isolate hippocampal contributions to memory. On each trial participants chose one of four options, but the reward probabilities for pairs of options were correlated across trials. This (uninstructed) relationship between pairs of options potentially enabled an observer to learn about option values based on experience with the other options and to generalize across them. We observed blood oxygen level-dependent (BOLD) activity related to learning in the striatum and also in the hippocampus. By comparing a basic reinforcement learning model to one augmented to allow feedback to generalize between correlated options, we tested whether choice behavior and BOLD activity were influenced by the opportunity to generalize across correlated options. Although such generalization goes beyond standard computational accounts of reinforcement learning and striatal BOLD, both choices and striatal BOLD activity were better explained by the augmented model. Consistent with the hypothesized role for the hippocampus in this generalization, functional connectivity between the ventral striatum and hippocampus was modulated, across participants, by the ability of the augmented model to capture participants' choice. Our results thus point toward an interactive model in which striatal reinforcement learning systems may employ relational representations typically associated with the hippocampus. © 2012 The Authors. European Journal of Neuroscience © 2012 Federation of European Neuroscience Societies and Blackwell Publishing Ltd.

Instrumental learning and relearning in individuals with psychopathy and in patients with lesions involving the amygdala or orbitofrontal cortex.

PubMed

Mitchell, D G V; Fine, C; Richell, R A; Newman, C; Lumsden, J; Blair, K S; Blair, R J R

2006-05-01

Previous work has shown that individuals with psychopathy are impaired on some forms of associative learning, particularly stimulus-reinforcement learning (Blair et al., 2004; Newman & Kosson, 1986). Animal work suggests that the acquisition of stimulus-reinforcement associations requires the amygdala (Baxter & Murray, 2002). Individuals with psychopathy also show impoverished reversal learning (Mitchell, Colledge, Leonard, & Blair, 2002). Reversal learning is supported by the ventrolateral and orbitofrontal cortex (Rolls, 2004). In this paper we present experiments investigating stimulus-reinforcement learning and relearning in patients with lesions of the orbitofrontal cortex or amygdala, and individuals with developmental psychopathy without known trauma. The results are interpreted with reference to current neurocognitive models of stimulus-reinforcement learning, relearning, and developmental psychopathy. Copyright (c) 2006 APA, all rights reserved.

Reinforcement of Science Learning through Local Culture: A Delphi Study

ERIC Educational Resources Information Center

Nuangchalerm, Prasart

2008-01-01

This study aims to explore the ways to reinforce science learning through local culture by using Delphi technique. Twenty four participants in various fields of study were selected. The result of study provides a framework for reinforcement of science learning through local culture on the theme life and environment. (Contains 1 table.)

Coherent controlization using superconducting qubits

PubMed Central

Friis, Nicolai; Melnikov, Alexey A.; Kirchmair, Gerhard; Briegel, Hans J.

2015-01-01

Coherent controlization, i.e., coherent conditioning of arbitrary single- or multi-qubit operations on the state of one or more control qubits, is an important ingredient for the flexible implementation of many algorithms in quantum computation. This is of particular significance when certain subroutines are changing over time or when they are frequently modified, such as in decision-making algorithms for learning agents. We propose a scheme to realize coherent controlization for any number of superconducting qubits coupled to a microwave resonator. For two and three qubits, we present an explicit construction that is of high relevance for quantum learning agents. We demonstrate the feasibility of our proposal, taking into account loss, dephasing, and the cavity self-Kerr effect. PMID:26667893

Online Learning of Genetic Network Programming and its Application to Prisoner’s Dilemma Game

NASA Astrophysics Data System (ADS)

Mabu, Shingo; Hirasawa, Kotaro; Hu, Jinglu; Murata, Junichi

A new evolutionary model with the network structure named Genetic Network Programming (GNP) has been proposed recently. GNP, that is, an expansion of GA and GP, represents solutions as a network structure and evolves it by using “offline learning (selection, mutation, crossover)”. GNP can memorize the past action sequences in the network flow, so it can deal with Partially Observable Markov Decision Process (POMDP) well. In this paper, in order to improve the ability of GNP, Q learning (an off-policy TD control algorithm) that is one of the famous online methods is introduced for online learning of GNP. Q learning is suitable for GNP because (1) in reinforcement learning, the rewards an agent will get in the future can be estimated, (2) TD control doesn’t need much memory and can learn quickly, and (3) off-policy is suitable in order to search for an optimal solution independently of the policy. Finally, in the simulations, online learning of GNP is applied to a player for “Prisoner’s dilemma game” and its ability for online adaptation is confirmed.

An incremental approach to genetic-algorithms-based classification.

PubMed

Guan, Sheng-Uei; Zhu, Fangming

2005-04-01

Incremental learning has been widely addressed in the machine learning literature to cope with learning tasks where the learning environment is ever changing or training samples become available over time. However, most research work explores incremental learning with statistical algorithms or neural networks, rather than evolutionary algorithms. The work in this paper employs genetic algorithms (GAs) as basic learning algorithms for incremental learning within one or more classifier agents in a multiagent environment. Four new approaches with different initialization schemes are proposed. They keep the old solutions and use an "integration" operation to integrate them with new elements to accommodate new attributes, while biased mutation and crossover operations are adopted to further evolve a reinforced solution. The simulation results on benchmark classification data sets show that the proposed approaches can deal with the arrival of new input attributes and integrate them with the original input space. It is also shown that the proposed approaches can be successfully used for incremental learning and improve classification rates as compared to the retraining GA. Possible applications for continuous incremental training and feature selection are also discussed.

Effect of dewatering on seismic performance of multi-anchor wall due to high ground water level

NASA Astrophysics Data System (ADS)

Kobayashi, Makoto; Miura, Kinya; Konami, Takeharu; Hayashi, Taketo; Sato, Hiroki

2017-10-01

Previous research reported that the ground water in the backfill of reinforced soil wall made it deteriorate. According to the damage investigation of Great East Earthquake 2011, the reinforced soil structure due to high ground water level by seismic wave were deformed remarkably. Some of them classified ultimate limit state or restorability limit state. However, more than 90% of reinforced soil structure, which suffered from this earthquake, were classified into no damage condition. Therefore, it is necessary that the seismic behaviors of multi-anchor wall due to seepage flow should be clarified in order to adopt the performance-based design in such reinforced soil structure. In this study, a series of centrifugal shaking table tests were conducted to investigate the seismic behavior of multi-anchor wall due to high ground water level. The reinforced drainage pipes were installed into the backfill in order to verify the dewatering effect and additional reinforcement. Furthermore, to check only the dewatering effect, the model tests was carried out with several ground water table that was modeled the case reinforced drainage pipes installed. The test results show unique behavior of reinforced region that moved integrally. This implies that the reinforced region has been behaved as if it became one mass, and this behavior make this structure increase seismic performance. Thus, the effectiveness of dewatering was observed remarkably because of decreasing the inertial force during earthquake.

Exploration for Agents with Different Personalities in Unknown Environments

NASA Astrophysics Data System (ADS)

Doumit, Sarjoun; Minai, Ali

We present in this paper a personality-based architecture (PA) that combines elements from the subsumption architecture and reinforcement learning to find alternate solutions for problems facing artificial agents exploring unknown environments. The underlying PA algorithm is decomposed into layers according to the different (non-contiguous) stages that our agent passes in, which in turn are influenced by the sources of rewards present in the environment. The cumulative rewards collected by an agent, in addition to its internal composition serve as factors in shaping its personality. In missions where multiple agents are deployed, our solution-goal is to allow each of the agents develop its own distinct personality in order for the collective to reach a balanced society, which then can accumulate the largest possible amount of rewards for the agent and society as well. The architecture is tested in a simulated matrix world which embodies different types of positive rewards and negative rewards. Varying experiments are performed to compare the performance of our algorithm with other algorithms under the same environment conditions. The use of our architecture accelerates the overall adaptation of the agents to their environment and goals by allowing the emergence of an optimal society of agents with different personalities. We believe that our approach achieves much efficient results when compared to other more restrictive policy designs.

Reinforcement mechanism of multi-anchor wall with double wall facing

NASA Astrophysics Data System (ADS)

Suzuki, Kouta; Kobayashi, Makoto; Miura, Kinya; Konami, Takeharu; Hayashi, Taketo

2017-10-01

The reinforced soil wall has high seismic performance as generally known. However, the seismic behavior has not been clarified accurately yet, especially on multi-anchor wall with double wall facing. Indefinite behavior of reinforced soil wall during earthquake make us complicated in case with adopting to the abutment, because of arrangement of anchor plate as reinforcement often different according to the width of roads. In this study, a series of centrifuge model tests were carried out to investigate the reinforcement mechanism of multi anchor wall with double wall facing from the perspective of the vertical earth pressure. Several types of reinforce arrangement and rigid wall were applied in order to verify the arch function in the reinforced regions. The test results show unique behavior of vertical earth pressure, which was affected by arch action. All the vertical earth pressure placed behind facing panel, are larger than that of middle part between facing panel despite of friction between backfill and facing panel. Similar results were obtained in case using rigid wall. On the other hands, the vertical earth pressure, which were measured at the 3cm high from bottom of model container, shows larger than that of bottom. This results show the existence of arch action between double walls. In addition, it implies that the wall facing of such soil structure confined the backfill as pseudo wall, which is very reason that the multi anchor wall with double wall facing has high seismic performance.

Measurement of ageing effect on chloride diffusion coefficients in cementitious matrices

NASA Astrophysics Data System (ADS)

Andrade, C.; Castellote, M.; d'Andrea, R.

2011-05-01

Most of the low-level nuclear waste disposal facilities are based in engineered multi barrier systems where reinforced concrete is one of the basic materials. The calculation of the time until steel reinforcement depassivation is a need due to the demand of prediction of the service life of concrete structures in radioactive repositories. In doing that, one of the main steps is the transport of chloride ions towards the reinforcement, as one of the most aggressive agents for the rebars in concrete is chloride ions. Ageing of concrete related to chloride penetration leads to significant decrease of the "apparent diffusion" coefficient with time. If this effect is not considered, considerable bias can be introduced when predicting service life of reinforced concrete of repositories. Several effects have been addressed on their influence on the ageing of concrete, including the evolution with time of the concrete pore refinement, the binding of chlorides to the cement phases and to the changes of chloride "surface concentration". These effects have been studied in specimens made with different mixes trying to represent a wide range of mineral addition proportions. The analysis of their evolution with time has shown that the resistivity alone or the joint consideration of resistivity and binding capacity ( Cb/ Cf), are appropriate parameters to appraise the diffusivity ageing. For practical reasons, an accelerated procedure is proposed in order to calculate ageing for short periods of time.

A Scaffolding Framework to Support Learning of Emergent Phenomena Using Multi-Agent-Based Simulation Environments

ERIC Educational Resources Information Center

Basu, Satabdi; Sengupta, Pratim; Biswas, Gautam

2015-01-01

Students from middle school to college have difficulties in interpreting and understanding complex systems such as ecological phenomena. Researchers have suggested that students experience difficulties in reconciling the relationships between individuals, populations, and species, as well as the interactions between organisms and their environment…

Designing across Ages: Multi-Agent-Based Models and Learning Electricity

ERIC Educational Resources Information Center

Sengupta, Pratim

2009-01-01

Electricity is regarded as one of the most challenging topics for students at all levels--middle school--college (Cohen, Eylon, & Ganiel, 1983; Belcher & Olbert, 2003; Eylon & Ganiel, 1990; Steinberg et al., 1985). Several researchers have suggested that naive misconceptions about electricity stem from a deep incommensurability (Slotta & Chi,…

Formal Methods for Information Protection Technology. Task 2: Mathematical Foundations, Architecture and Principles of Implementation of Multi-Agent Learning Components for Attack Detection in Computer Networks. Part 2

DTIC Science & Technology

2003-11-01

Lafayette, IN 47907. [Lane et al-97b] T. Lane and C . E. Brodley. Sequence matching and learning in anomaly detection for computer security. Proceedings of...Mining, pp 259-263. 1998. [Lane et al-98b] T. Lane and C . E. Brodley. Temporal sequence learning and data reduction for anomaly detection ...W. Lee, C . Park, and S. Stolfo. Towards Automatic Intrusion Detection using NFR. 1st USENIX Workshop on Intrusion Detection and Network Monitoring

A Threshold Model for Opposing Actions of Acetylcholine on Reward Behavior: Molecular Mechanisms and Implications for Treatment of Substance Abuse Disorders

PubMed Central

Grasing, Kenneth

2016-01-01

The cholinergic system plays important roles in both learning and addiction. Medications that modify cholinergic tone can have pronounced effects on behaviors reinforced by natural and drug reinforcers. Importantly, enhancing the action of acetylcholine (ACh) in the nucleus accumbens and ventral tegmental area (VTA) dopamine system can either augment or diminish these behaviors. A threshold model is presented that can explain these seemingly contradictory results. Relatively low levels of ACh rise above a lower threshold, facilitating behaviors supported by drugs or natural reinforcers. Further increases in cholinergic tone that rise above a second upper threshold oppose the same behaviors. Accordingly, cholinesterase inhibitors, or agonists for nicotinic or muscarinic receptors, each have the potential to produce biphasic effects on reward behaviors. Pretreatment with either nicotinic or muscarinic antagonists can block drug- or food- reinforced behavior by maintaining cholinergic tone below its lower threshold. Potential threshold mediators include desensitization of nicotinic receptors and biphasic effects of ACh on the firing of medium spiny neurons. Nicotinic receptors with high- and low-affinity appear to play greater roles in reward enhancement and inhibition, respectively. Cholinergic inhibition of natural and drug rewards may serve as mediators of previously described opponent processes. Future studies should evaluate cholinergic agents across a broader range of doses, and include a variety of reinforced behaviors. PMID:27316344

Partial Planning Reinforcement Learning

DTIC Science & Technology

2012-08-31

Research Office P.O. Box 12211 Research Triangle Park, NC 27709-2211 15. SUBJECT TERMS Reinforcement Learning, Bayesian Optimization, Active ... Learning , Action Model Learning, Decision Theoretic Assistance Prasad Tadepalli, Alan Fern Oregon State University Office of Sponsored Programs Oregon State

Localization Transition Induced by Learning in Random Searches

NASA Astrophysics Data System (ADS)

Falcón-Cortés, Andrea; Boyer, Denis; Giuggioli, Luca; Majumdar, Satya N.

2017-10-01

We solve an adaptive search model where a random walker or Lévy flight stochastically resets to previously visited sites on a d -dimensional lattice containing one trapping site. Because of reinforcement, a phase transition occurs when the resetting rate crosses a threshold above which nondiffusive stationary states emerge, localized around the inhomogeneity. The threshold depends on the trapping strength and on the walker's return probability in the memoryless case. The transition belongs to the same class as the self-consistent theory of Anderson localization. These results show that similarly to many living organisms and unlike the well-studied Markovian walks, non-Markov movement processes can allow agents to learn about their environment and promise to bring adaptive solutions in search tasks.

Thermoplastic polymides and composites therefrom

NASA Technical Reports Server (NTRS)

Harris, Frank W. (Inventor)

1994-01-01

A new class polyimide and polyimide precursors based on diaryl oxyalkylene diamines, such as 1,3-bis[4-aminophenoxy]-2,2-dimethyl propane, a process for their preparation and their use as the continuous phase for the manufacture of composites and composite laminates reinforced by reinforcing agents such as carbon fibers, Kevlar.TM., and other similar high strength reinforcing agents. The polyimides and molecular composites obtained from the diamines according to the invention show thermoplastic properties, excellent flex fatigue and fracture resistance, and excellent thermal and oxidative stability.

Exploring complex dynamics in multi agent-based intelligent systems: Theoretical and experimental approaches using the Multi Agent-based Behavioral Economic Landscape (MABEL) model

NASA Astrophysics Data System (ADS)

Alexandridis, Konstantinos T.

This dissertation adopts a holistic and detailed approach to modeling spatially explicit agent-based artificial intelligent systems, using the Multi Agent-based Behavioral Economic Landscape (MABEL) model. The research questions that addresses stem from the need to understand and analyze the real-world patterns and dynamics of land use change from a coupled human-environmental systems perspective. Describes the systemic, mathematical, statistical, socio-economic and spatial dynamics of the MABEL modeling framework, and provides a wide array of cross-disciplinary modeling applications within the research, decision-making and policy domains. Establishes the symbolic properties of the MABEL model as a Markov decision process, analyzes the decision-theoretic utility and optimization attributes of agents towards comprising statistically and spatially optimal policies and actions, and explores the probabilogic character of the agents' decision-making and inference mechanisms via the use of Bayesian belief and decision networks. Develops and describes a Monte Carlo methodology for experimental replications of agent's decisions regarding complex spatial parcel acquisition and learning. Recognizes the gap on spatially-explicit accuracy assessment techniques for complex spatial models, and proposes an ensemble of statistical tools designed to address this problem. Advanced information assessment techniques such as the Receiver-Operator Characteristic curve, the impurity entropy and Gini functions, and the Bayesian classification functions are proposed. The theoretical foundation for modular Bayesian inference in spatially-explicit multi-agent artificial intelligent systems, and the ensembles of cognitive and scenario assessment modular tools build for the MABEL model are provided. Emphasizes the modularity and robustness as valuable qualitative modeling attributes, and examines the role of robust intelligent modeling as a tool for improving policy-decisions related to land use change. Finally, the major contributions to the science are presented along with valuable directions for future research.

Reinforcement learning in scheduling

NASA Technical Reports Server (NTRS)

Dietterich, Tom G.; Ok, Dokyeong; Zhang, Wei; Tadepalli, Prasad

1994-01-01

The goal of this research is to apply reinforcement learning methods to real-world problems like scheduling. In this preliminary paper, we show that learning to solve scheduling problems such as the Space Shuttle Payload Processing and the Automatic Guided Vehicle (AGV) scheduling can be usefully studied in the reinforcement learning framework. We discuss some of the special challenges posed by the scheduling domain to these methods and propose some possible solutions we plan to implement.

Neural Basis of Reinforcement Learning and Decision Making

PubMed Central

Lee, Daeyeol; Seo, Hyojung; Jung, Min Whan

2012-01-01

Reinforcement learning is an adaptive process in which an animal utilizes its previous experience to improve the outcomes of future choices. Computational theories of reinforcement learning play a central role in the newly emerging areas of neuroeconomics and decision neuroscience. In this framework, actions are chosen according to their value functions, which describe how much future reward is expected from each action. Value functions can be adjusted not only through reward and penalty, but also by the animal’s knowledge of its current environment. Studies have revealed that a large proportion of the brain is involved in representing and updating value functions and using them to choose an action. However, how the nature of a behavioral task affects the neural mechanisms of reinforcement learning remains incompletely understood. Future studies should uncover the principles by which different computational elements of reinforcement learning are dynamically coordinated across the entire brain. PMID:22462543

The curse of planning: dissecting multiple reinforcement-learning systems by taxing the central executive.

PubMed

Otto, A Ross; Gershman, Samuel J; Markman, Arthur B; Daw, Nathaniel D

2013-05-01

A number of accounts of human and animal behavior posit the operation of parallel and competing valuation systems in the control of choice behavior. In these accounts, a flexible but computationally expensive model-based reinforcement-learning system has been contrasted with a less flexible but more efficient model-free reinforcement-learning system. The factors governing which system controls behavior-and under what circumstances-are still unclear. Following the hypothesis that model-based reinforcement learning requires cognitive resources, we demonstrated that having human decision makers perform a demanding secondary task engenders increased reliance on a model-free reinforcement-learning strategy. Further, we showed that, across trials, people negotiate the trade-off between the two systems dynamically as a function of concurrent executive-function demands, and people's choice latencies reflect the computational expenses of the strategy they employ. These results demonstrate that competition between multiple learning systems can be controlled on a trial-by-trial basis by modulating the availability of cognitive resources.

The Curse of Planning: Dissecting multiple reinforcement learning systems by taxing the central executive

PubMed Central

Otto, A. Ross; Gershman, Samuel J.; Markman, Arthur B.; Daw, Nathaniel D.

2013-01-01

A number of accounts of human and animal behavior posit the operation of parallel and competing valuation systems in the control of choice behavior. Along these lines, a flexible but computationally expensive model-based reinforcement learning system has been contrasted with a less flexible but more efficient model-free reinforcement learning system. The factors governing which system controls behavior—and under what circumstances—are still unclear. Based on the hypothesis that model-based reinforcement learning requires cognitive resources, we demonstrate that having human decision-makers perform a demanding secondary task engenders increased reliance on a model-free reinforcement learning strategy. Further, we show that across trials, people negotiate this tradeoff dynamically as a function of concurrent executive function demands and their choice latencies reflect the computational expenses of the strategy employed. These results demonstrate that competition between multiple learning systems can be controlled on a trial-by-trial basis by modulating the availability of cognitive resources. PMID:23558545

On-lattice agent-based simulation of populations of cells within the open-source Chaste framework.

PubMed

Figueredo, Grazziela P; Joshi, Tanvi V; Osborne, James M; Byrne, Helen M; Owen, Markus R

2013-04-06

Over the years, agent-based models have been developed that combine cell division and reinforced random walks of cells on a regular lattice, reaction-diffusion equations for nutrients and growth factors; and ordinary differential equations for the subcellular networks regulating the cell cycle. When linked to a vascular layer, this multiple scale model framework has been applied to tumour growth and therapy. Here, we report on the creation of an agent-based multi-scale environment amalgamating the characteristics of these models within a Virtual Physiological Human (VPH) Exemplar Project. This project enables reuse, integration, expansion and sharing of the model and relevant data. The agent-based and reaction-diffusion parts of the multi-scale model have been implemented and are available for download as part of the latest public release of Chaste (Cancer, Heart and Soft Tissue Environment; http://www.cs.ox.ac.uk/chaste/), part of the VPH Toolkit (http://toolkit.vph-noe.eu/). The environment functionalities are verified against the original models, in addition to extra validation of all aspects of the code. In this work, we present the details of the implementation of the agent-based environment, including the system description, the conceptual model, the development of the simulation model and the processes of verification and validation of the simulation results. We explore the potential use of the environment by presenting exemplar applications of the 'what if' scenarios that can easily be studied in the environment. These examples relate to tumour growth, cellular competition for resources and tumour responses to hypoxia (low oxygen levels). We conclude our work by summarizing the future steps for the expansion of the current system.

Self-Paced Prioritized Curriculum Learning With Coverage Penalty in Deep Reinforcement Learning.

PubMed

Ren, Zhipeng; Dong, Daoyi; Li, Huaxiong; Chen, Chunlin; Zhipeng Ren; Daoyi Dong; Huaxiong Li; Chunlin Chen; Dong, Daoyi; Li, Huaxiong; Chen, Chunlin; Ren, Zhipeng

2018-06-01

In this paper, a new training paradigm is proposed for deep reinforcement learning using self-paced prioritized curriculum learning with coverage penalty. The proposed deep curriculum reinforcement learning (DCRL) takes the most advantage of experience replay by adaptively selecting appropriate transitions from replay memory based on the complexity of each transition. The criteria of complexity in DCRL consist of self-paced priority as well as coverage penalty. The self-paced priority reflects the relationship between the temporal-difference error and the difficulty of the current curriculum for sample efficiency. The coverage penalty is taken into account for sample diversity. With comparison to deep Q network (DQN) and prioritized experience replay (PER) methods, the DCRL algorithm is evaluated on Atari 2600 games, and the experimental results show that DCRL outperforms DQN and PER on most of these games. More results further show that the proposed curriculum training paradigm of DCRL is also applicable and effective for other memory-based deep reinforcement learning approaches, such as double DQN and dueling network. All the experimental results demonstrate that DCRL can achieve improved training efficiency and robustness for deep reinforcement learning.

Using Fuzzy Logic for Performance Evaluation in Reinforcement Learning

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.; Khedkar, Pratap S.

1992-01-01

Current reinforcement learning algorithms require long training periods which generally limit their applicability to small size problems. A new architecture is described which uses fuzzy rules to initialize its two neural networks: a neural network for performance evaluation and another for action selection. This architecture is applied to control of dynamic systems and it is demonstrated that it is possible to start with an approximate prior knowledge and learn to refine it through experiments using reinforcement learning.

Reinforcement learning in multidimensional environments relies on attention mechanisms.

PubMed

Niv, Yael; Daniel, Reka; Geana, Andra; Gershman, Samuel J; Leong, Yuan Chang; Radulescu, Angela; Wilson, Robert C

2015-05-27

In recent years, ideas from the computational field of reinforcement learning have revolutionized the study of learning in the brain, famously providing new, precise theories of how dopamine affects learning in the basal ganglia. However, reinforcement learning algorithms are notorious for not scaling well to multidimensional environments, as is required for real-world learning. We hypothesized that the brain naturally reduces the dimensionality of real-world problems to only those dimensions that are relevant to predicting reward, and conducted an experiment to assess by what algorithms and with what neural mechanisms this "representation learning" process is realized in humans. Our results suggest that a bilateral attentional control network comprising the intraparietal sulcus, precuneus, and dorsolateral prefrontal cortex is involved in selecting what dimensions are relevant to the task at hand, effectively updating the task representation through trial and error. In this way, cortical attention mechanisms interact with learning in the basal ganglia to solve the "curse of dimensionality" in reinforcement learning. Copyright © 2015 the authors 0270-6474/15/358145-13$15.00/0.

Changes in corticostriatal connectivity during reinforcement learning in humans.

PubMed

Horga, Guillermo; Maia, Tiago V; Marsh, Rachel; Hao, Xuejun; Xu, Dongrong; Duan, Yunsuo; Tau, Gregory Z; Graniello, Barbara; Wang, Zhishun; Kangarlu, Alayar; Martinez, Diana; Packard, Mark G; Peterson, Bradley S

2015-02-01

Many computational models assume that reinforcement learning relies on changes in synaptic efficacy between cortical regions representing stimuli and striatal regions involved in response selection, but this assumption has thus far lacked empirical support in humans. We recorded hemodynamic signals with fMRI while participants navigated a virtual maze to find hidden rewards. We fitted a reinforcement-learning algorithm to participants' choice behavior and evaluated the neural activity and the changes in functional connectivity related to trial-by-trial learning variables. Activity in the posterior putamen during choice periods increased progressively during learning. Furthermore, the functional connections between the sensorimotor cortex and the posterior putamen strengthened progressively as participants learned the task. These changes in corticostriatal connectivity differentiated participants who learned the task from those who did not. These findings provide a direct link between changes in corticostriatal connectivity and learning, thereby supporting a central assumption common to several computational models of reinforcement learning. © 2014 Wiley Periodicals, Inc.

A common neural circuit mechanism for internally guided and externally reinforced forms of motor learning.

PubMed

Hisey, Erin; Kearney, Matthew Gene; Mooney, Richard

2018-04-01

The complex skills underlying verbal and musical expression can be learned without external punishment or reward, indicating their learning is internally guided. The neural mechanisms that mediate internally guided learning are poorly understood, but a circuit comprising dopamine-releasing neurons in the midbrain ventral tegmental area (VTA) and their targets in the basal ganglia are important to externally reinforced learning. Juvenile zebra finches copy a tutor song in a process that is internally guided and, in adulthood, can learn to modify the fundamental frequency (pitch) of a target syllable in response to external reinforcement with white noise. Here we combined intersectional genetic ablation of VTA neurons, reversible blockade of dopamine receptors in the basal ganglia, and singing-triggered optogenetic stimulation of VTA terminals to establish that a common VTA-basal ganglia circuit enables internally guided song copying and externally reinforced syllable pitch learning.

Knockout crickets for the study of learning and memory: Dopamine receptor Dop1 mediates aversive but not appetitive reinforcement in crickets.

PubMed

Awata, Hiroko; Watanabe, Takahito; Hamanaka, Yoshitaka; Mito, Taro; Noji, Sumihare; Mizunami, Makoto

2015-11-02

Elucidation of reinforcement mechanisms in associative learning is an important subject in neuroscience. In mammals, dopamine neurons are thought to play critical roles in mediating both appetitive and aversive reinforcement. Our pharmacological studies suggested that octopamine and dopamine neurons mediate reward and punishment, respectively, in crickets, but recent studies in fruit-flies concluded that dopamine neurons mediates both reward and punishment, via the type 1 dopamine receptor Dop1. To resolve the discrepancy between studies in different insect species, we produced Dop1 knockout crickets using the CRISPR/Cas9 system and found that they are defective in aversive learning with sodium chloride punishment but not appetitive learning with water or sucrose reward. The results suggest that dopamine and octopamine neurons mediate aversive and appetitive reinforcement, respectively, in crickets. We suggest unexpected diversity in neurotransmitters mediating appetitive reinforcement between crickets and fruit-flies, although the neurotransmitter mediating aversive reinforcement is conserved. This study demonstrates usefulness of the CRISPR/Cas9 system for producing knockout animals for the study of learning and memory.

Spore: Spawning Evolutionary Misconceptions?

NASA Astrophysics Data System (ADS)

Bean, Thomas E.; Sinatra, Gale M.; Schrader, P. G.

2010-10-01

The use of computer simulations as educational tools may afford the means to develop understanding of evolution as a natural, emergent, and decentralized process. However, special consideration of developmental constraints on learning may be necessary when using these technologies. Specifically, the essentialist (biological forms possess an immutable essence), teleological (assignment of purpose to living things and/or parts of living things that may not be purposeful), and intentionality (assumption that events are caused by an intelligent agent) biases may be reinforced through the use of computer simulations, rather than addressed with instruction. We examine the video game Spore for its depiction of evolutionary content and its potential to reinforce these cognitive biases. In particular, we discuss three pedagogical strategies to mitigate weaknesses of Spore and other computer simulations: directly targeting misconceptions through refutational approaches, targeting specific principles of scientific inquiry, and directly addressing issues related to models as cognitive tools.

Adhesion and Interphase Properties of Reinforced Polymeric Composites

NASA Astrophysics Data System (ADS)

Caldwell, Kyle Bernd

Reinforced polymeric composites are an increasingly utilized material with a wide range of applications. Fiber reinforced polymeric composites, in particular, possess impressive mechanical properties at a fraction of the weight of many other building materials. There will always, however, be a demand for producing lighter, stiffer, and stronger materials. Understanding the mechanism of adhesion and ways to engineer the reinforcement-matrix interphase can lead to the development of new materials with improved mechanical properties, and even impart additional functionality such as electrical conductivity. The performance of reinforced polymeric composites is critically dependent upon the adhesion between the reinforcement and the surrounding polymer. The relative adhesion between a filler and a thermoplastic matrix can be predicted using calculable thermodynamic quantities such as the Gibbs free energy of mixing. A recent model, COSMO-SAC, is capable of predicting the adhesion between organo-silane treated glass surfaces and several thermoplastic materials. COSMO-SAC uses information based on the charge distribution of a molecule's surface to calculate many thermodynamic properties. Density functional theory calculations, which are relative inexpensive computations, generate the information necessary to perform the COSMO-SAC analysis and can be performed on any given molecule. The flexibility of the COSMO-SAC model is one of the main advantages it possesses over other methods for calculating thermodynamic quantities. In many cases the adhesion between a reinforcing fiber and the surrounding matrix may be improved by incorporating interphase modifiers in the vicinity of the fiber surface. The modifiers can improve the fracture toughness and modulus of the interphase, which may improve the stress transfer from the matrix to the fiber. In addition, the interphase modifiers may improve the mechanical interlock between the fiber surface and the bulk polymer, leading to improved adhesion. In recent years, the use of so called "migrating agents" have been used to self-assemble nanoparticle reinforced fiber-matrix interphases in thermosetting resin systems. The inclusion of a modest amount of thermoplastic migrating agent can lead to the formation of a self-assembled interphase, without causing aggregation of nanoparticles in the bulk phase. Formulations containing excess migrating agent, however, can induce aggregation in the bulk of increasing severity with increasing migrating agent concentration. Several techniques were used to study the mechanism by which the migrating agents operate including, scanning electron microscopy, and in situ fluorescence microscopy. The self-assembly mechanism by which migrating agents operate is described well by depletion forces, which are depend on the geometry of the approaching objects, as well as the migrating agent molecular weight and concentration.

Social Cognition as Reinforcement Learning: Feedback Modulates Emotion Inference.

PubMed

Zaki, Jamil; Kallman, Seth; Wimmer, G Elliott; Ochsner, Kevin; Shohamy, Daphna

2016-09-01

Neuroscientific studies of social cognition typically employ paradigms in which perceivers draw single-shot inferences about the internal states of strangers. Real-world social inference features much different parameters: People often encounter and learn about particular social targets (e.g., friends) over time and receive feedback about whether their inferences are correct or incorrect. Here, we examined this process and, more broadly, the intersection between social cognition and reinforcement learning. Perceivers were scanned using fMRI while repeatedly encountering three social targets who produced conflicting visual and verbal emotional cues. Perceivers guessed how targets felt and received feedback about whether they had guessed correctly. Visual cues reliably predicted one target's emotion, verbal cues predicted a second target's emotion, and neither reliably predicted the third target's emotion. Perceivers successfully used this information to update their judgments over time. Furthermore, trial-by-trial learning signals-estimated using two reinforcement learning models-tracked activity in ventral striatum and ventromedial pFC, structures associated with reinforcement learning, and regions associated with updating social impressions, including TPJ. These data suggest that learning about others' emotions, like other forms of feedback learning, relies on domain-general reinforcement mechanisms as well as domain-specific social information processing.

Memory Transformation Enhances Reinforcement Learning in Dynamic Environments.

PubMed

Santoro, Adam; Frankland, Paul W; Richards, Blake A

2016-11-30

Over the course of systems consolidation, there is a switch from a reliance on detailed episodic memories to generalized schematic memories. This switch is sometimes referred to as "memory transformation." Here we demonstrate a previously unappreciated benefit of memory transformation, namely, its ability to enhance reinforcement learning in a dynamic environment. We developed a neural network that is trained to find rewards in a foraging task where reward locations are continuously changing. The network can use memories for specific locations (episodic memories) and statistical patterns of locations (schematic memories) to guide its search. We find that switching from an episodic to a schematic strategy over time leads to enhanced performance due to the tendency for the reward location to be highly correlated with itself in the short-term, but regress to a stable distribution in the long-term. We also show that the statistics of the environment determine the optimal utilization of both types of memory. Our work recasts the theoretical question of why memory transformation occurs, shifting the focus from the avoidance of memory interference toward the enhancement of reinforcement learning across multiple timescales. As time passes, memories transform from a highly detailed state to a more gist-like state, in a process called "memory transformation." Theories of memory transformation speak to its advantages in terms of reducing memory interference, increasing memory robustness, and building models of the environment. However, the role of memory transformation from the perspective of an agent that continuously acts and receives reward in its environment is not well explored. In this work, we demonstrate a view of memory transformation that defines it as a way of optimizing behavior across multiple timescales. Copyright © 2016 the authors 0270-6474/16/3612228-15$15.00/0.

Probabilistic Reinforcement Learning in Adults with Autism Spectrum Disorders

PubMed Central

Solomon, Marjorie; Smith, Anne C.; Frank, Michael J.; Ly, Stanford; Carter, Cameron S.

2017-01-01

Background Autism spectrum disorders (ASDs) can be conceptualized as disorders of learning, however there have been few experimental studies taking this perspective. Methods We examined the probabilistic reinforcement learning performance of 28 adults with ASDs and 30 typically developing adults on a task requiring learning relationships between three stimulus pairs consisting of Japanese characters with feedback that was valid with different probabilities (80%, 70%, and 60%). Both univariate and Bayesian state–space data analytic methods were employed. Hypotheses were based on the extant literature as well as on neurobiological and computational models of reinforcement learning. Results Both groups learned the task after training. However, there were group differences in early learning in the first task block where individuals with ASDs acquired the most frequently accurately reinforced stimulus pair (80%) comparably to typically developing individuals; exhibited poorer acquisition of the less frequently reinforced 70% pair as assessed by state–space learning curves; and outperformed typically developing individuals on the near chance (60%) pair. Individuals with ASDs also demonstrated deficits in using positive feedback to exploit rewarded choices. Conclusions Results support the contention that individuals with ASDs are slower learners. Based on neurobiology and on the results of computational modeling, one interpretation of this pattern of findings is that impairments are related to deficits in flexible updating of reinforcement history as mediated by the orbito-frontal cortex, with spared functioning of the basal ganglia. This hypothesis about the pathophysiology of learning in ASDs can be tested using functional magnetic resonance imaging. PMID:21425243

Cells, Agents, and Support Vectors in Interaction - Modeling Urban Sprawl based on Machine Learning and Artificial Intelligence Techniques in a Post-Industrial Region

NASA Astrophysics Data System (ADS)

Rienow, A.; Menz, G.

2015-12-01

Since the beginning of the millennium, artificial intelligence techniques as cellular automata (CA) and multi-agent systems (MAS) have been incorporated into land-system simulations to address the complex challenges of transitions in urban areas as open, dynamic systems. The study presents a hybrid modeling approach for modeling the two antagonistic processes of urban sprawl and urban decline at once. The simulation power of support vector machines (SVM), cellular automata (CA) and multi-agent systems (MAS) are integrated into one modeling framework and applied to the largest agglomeration of Central Europe: the Ruhr. A modified version of SLEUTH (short for Slope, Land-use, Exclusion, Urban, Transport, and Hillshade) functions as the CA component. SLEUTH makes use of historic urban land-use data sets and growth coefficients for the purpose of modeling physical urban expansion. The machine learning algorithm of SVM is applied in order to enhance SLEUTH. Thus, the stochastic variability of the CA is reduced and information about the human and ecological forces driving the local suitability of urban sprawl is incorporated. Subsequently, the supported CA is coupled with the MAS ReHoSh (Residential Mobility and the Housing Market of Shrinking City Systems). The MAS models population patterns, housing prices, and housing demand in shrinking regions based on interactions between household and city agents. Semi-explicit urban weights are introduced as a possibility of modeling from and to the pixel simultaneously. Three scenarios of changing housing preferences reveal the urban development of the region in terms of quantity and location. They reflect the dissemination of sustainable thinking among stakeholders versus the steady dream of owning a house in sub- and exurban areas. Additionally, the outcomes are transferred into a digital petri dish reflecting a synthetic environment with perfect conditions of growth. Hence, the generic growth elements affecting the future face of post-industrial cities are revealed. Finally, the advantages and limitations of linking pixels and people by combining AI and machine learning techniques in a multi-scale geosimulation approach are to be discussed.

Role of dopamine D2 receptors in human reinforcement learning.

PubMed

Eisenegger, Christoph; Naef, Michael; Linssen, Anke; Clark, Luke; Gandamaneni, Praveen K; Müller, Ulrich; Robbins, Trevor W

2014-09-01

Influential neurocomputational models emphasize dopamine (DA) as an electrophysiological and neurochemical correlate of reinforcement learning. However, evidence of a specific causal role of DA receptors in learning has been less forthcoming, especially in humans. Here we combine, in a between-subjects design, administration of a high dose of the selective DA D2/3-receptor antagonist sulpiride with genetic analysis of the DA D2 receptor in a behavioral study of reinforcement learning in a sample of 78 healthy male volunteers. In contrast to predictions of prevailing models emphasizing DA's pivotal role in learning via prediction errors, we found that sulpiride did not disrupt learning, but rather induced profound impairments in choice performance. The disruption was selective for stimuli indicating reward, whereas loss avoidance performance was unaffected. Effects were driven by volunteers with higher serum levels of the drug, and in those with genetically determined lower density of striatal DA D2 receptors. This is the clearest demonstration to date for a causal modulatory role of the DA D2 receptor in choice performance that might be distinct from learning. Our findings challenge current reward prediction error models of reinforcement learning, and suggest that classical animal models emphasizing a role of postsynaptic DA D2 receptors in motivational aspects of reinforcement learning may apply to humans as well.

Role of Dopamine D2 Receptors in Human Reinforcement Learning

PubMed Central

Eisenegger, Christoph; Naef, Michael; Linssen, Anke; Clark, Luke; Gandamaneni, Praveen K; Müller, Ulrich; Robbins, Trevor W

2014-01-01

Influential neurocomputational models emphasize dopamine (DA) as an electrophysiological and neurochemical correlate of reinforcement learning. However, evidence of a specific causal role of DA receptors in learning has been less forthcoming, especially in humans. Here we combine, in a between-subjects design, administration of a high dose of the selective DA D2/3-receptor antagonist sulpiride with genetic analysis of the DA D2 receptor in a behavioral study of reinforcement learning in a sample of 78 healthy male volunteers. In contrast to predictions of prevailing models emphasizing DA's pivotal role in learning via prediction errors, we found that sulpiride did not disrupt learning, but rather induced profound impairments in choice performance. The disruption was selective for stimuli indicating reward, whereas loss avoidance performance was unaffected. Effects were driven by volunteers with higher serum levels of the drug, and in those with genetically determined lower density of striatal DA D2 receptors. This is the clearest demonstration to date for a causal modulatory role of the DA D2 receptor in choice performance that might be distinct from learning. Our findings challenge current reward prediction error models of reinforcement learning, and suggest that classical animal models emphasizing a role of postsynaptic DA D2 receptors in motivational aspects of reinforcement learning may apply to humans as well. PMID:24713613

Construction of Multi-Mode Affective Learning System: Taking Affective Design as an Example

ERIC Educational Resources Information Center

Lin, Hao-Chiang Koong; Su, Sheng-Hsiung; Chao, Ching-Ju; Hsieh, Cheng-Yen; Tsai, Shang-Chin

2016-01-01

This study aims to design a non-simultaneous distance instruction system with affective computing, which integrates interactive agent technology with the curricular instruction of affective design. The research subjects were 78 students, and prototype assessment and final assessment were adopted to assess the interface and usability of the system.…

Student Query Trend Assessment with Semantical Annotation and Artificial Intelligent Multi-Agents

ERIC Educational Resources Information Center

Malik, Kaleem Razzaq; Mir, Rizwan Riaz; Farhan, Muhammad; Rafiq, Tariq; Aslam, Muhammad

2017-01-01

Research in era of data representation to contribute and improve key data policy involving the assessment of learning, training and English language competency. Students are required to communicate in English with high level impact using language and influence. The electronic technology works to assess students' questions positively enabling…

Reinforcement learning in computer vision

NASA Astrophysics Data System (ADS)

Bernstein, A. V.; Burnaev, E. V.

2018-04-01

Nowadays, machine learning has become one of the basic technologies used in solving various computer vision tasks such as feature detection, image segmentation, object recognition and tracking. In many applications, various complex systems such as robots are equipped with visual sensors from which they learn state of surrounding environment by solving corresponding computer vision tasks. Solutions of these tasks are used for making decisions about possible future actions. It is not surprising that when solving computer vision tasks we should take into account special aspects of their subsequent application in model-based predictive control. Reinforcement learning is one of modern machine learning technologies in which learning is carried out through interaction with the environment. In recent years, Reinforcement learning has been used both for solving such applied tasks as processing and analysis of visual information, and for solving specific computer vision problems such as filtering, extracting image features, localizing objects in scenes, and many others. The paper describes shortly the Reinforcement learning technology and its use for solving computer vision problems.

Reinforcement Learning in Multidimensional Environments Relies on Attention Mechanisms

PubMed Central

Daniel, Reka; Geana, Andra; Gershman, Samuel J.; Leong, Yuan Chang; Radulescu, Angela; Wilson, Robert C.

2015-01-01

In recent years, ideas from the computational field of reinforcement learning have revolutionized the study of learning in the brain, famously providing new, precise theories of how dopamine affects learning in the basal ganglia. However, reinforcement learning algorithms are notorious for not scaling well to multidimensional environments, as is required for real-world learning. We hypothesized that the brain naturally reduces the dimensionality of real-world problems to only those dimensions that are relevant to predicting reward, and conducted an experiment to assess by what algorithms and with what neural mechanisms this “representation learning” process is realized in humans. Our results suggest that a bilateral attentional control network comprising the intraparietal sulcus, precuneus, and dorsolateral prefrontal cortex is involved in selecting what dimensions are relevant to the task at hand, effectively updating the task representation through trial and error. In this way, cortical attention mechanisms interact with learning in the basal ganglia to solve the “curse of dimensionality” in reinforcement learning. PMID:26019331

Network congestion control algorithm based on Actor-Critic reinforcement learning model

NASA Astrophysics Data System (ADS)

Xu, Tao; Gong, Lina; Zhang, Wei; Li, Xuhong; Wang, Xia; Pan, Wenwen

2018-04-01

Aiming at the network congestion control problem, a congestion control algorithm based on Actor-Critic reinforcement learning model is designed. Through the genetic algorithm in the congestion control strategy, the network congestion problems can be better found and prevented. According to Actor-Critic reinforcement learning, the simulation experiment of network congestion control algorithm is designed. The simulation experiments verify that the AQM controller can predict the dynamic characteristics of the network system. Moreover, the learning strategy is adopted to optimize the network performance, and the dropping probability of packets is adaptively adjusted so as to improve the network performance and avoid congestion. Based on the above finding, it is concluded that the network congestion control algorithm based on Actor-Critic reinforcement learning model can effectively avoid the occurrence of TCP network congestion.

From Recurrent Choice to Skill Learning: A Reinforcement-Learning Model

ERIC Educational Resources Information Center

Fu, Wai-Tat; Anderson, John R.

2006-01-01

The authors propose a reinforcement-learning mechanism as a model for recurrent choice and extend it to account for skill learning. The model was inspired by recent research in neurophysiological studies of the basal ganglia and provides an integrated explanation of recurrent choice behavior and skill learning. The behavior includes effects of…

Crack Identification in CFRP Laminated Beams Using Multi-Resolution Modal Teager–Kaiser Energy under Noisy Environments

PubMed Central

Xu, Wei; Cao, Maosen; Ding, Keqin; Radzieński, Maciej; Ostachowicz, Wiesław

2017-01-01

Carbon fiber reinforced polymer laminates are increasingly used in the aerospace and civil engineering fields. Identifying cracks in carbon fiber reinforced polymer laminated beam components is of considerable significance for ensuring the integrity and safety of the whole structures. With the development of high-resolution measurement technologies, mode-shape-based crack identification in such laminated beam components has become an active research focus. Despite its sensitivity to cracks, however, this method is susceptible to noise. To address this deficiency, this study proposes a new concept of multi-resolution modal Teager–Kaiser energy, which is the Teager–Kaiser energy of a mode shape represented in multi-resolution, for identifying cracks in carbon fiber reinforced polymer laminated beams. The efficacy of this concept is analytically demonstrated by identifying cracks in Timoshenko beams with general boundary conditions; and its applicability is validated by diagnosing cracks in a carbon fiber reinforced polymer laminated beam, whose mode shapes are precisely acquired via non-contact measurement using a scanning laser vibrometer. The analytical and experimental results show that multi-resolution modal Teager–Kaiser energy is capable of designating the presence and location of cracks in these beams under noisy environments. This proposed method holds promise for developing crack identification systems for carbon fiber reinforced polymer laminates. PMID:28773016

Adolescent-specific patterns of behavior and neural activity during social reinforcement learning

PubMed Central

Jones, Rebecca M.; Somerville, Leah H.; Li, Jian; Ruberry, Erika J.; Powers, Alisa; Mehta, Natasha; Dyke, Jonathan; Casey, BJ

2014-01-01

Humans are sophisticated social beings. Social cues from others are exceptionally salient, particularly during adolescence. Understanding how adolescents interpret and learn from variable social signals can provide insight into the observed shift in social sensitivity during this period. The current study tested 120 participants between the ages of 8 and 25 years on a social reinforcement learning task where the probability of receiving positive social feedback was parametrically manipulated. Seventy-eight of these participants completed the task during fMRI scanning. Modeling trial-by-trial learning, children and adults showed higher positive learning rates than adolescents, suggesting that adolescents demonstrated less differentiation in their reaction times for peers who provided more positive feedback. Forming expectations about receiving positive social reinforcement correlated with neural activity within the medial prefrontal cortex and ventral striatum across age. Adolescents, unlike children and adults, showed greater insular activity during positive prediction error learning and increased activity in the supplementary motor cortex and the putamen when receiving positive social feedback regardless of the expected outcome, suggesting that peer approval may motivate adolescents towards action. While different amounts of positive social reinforcement enhanced learning in children and adults, all positive social reinforcement equally motivated adolescents. Together, these findings indicate that sensitivity to peer approval during adolescence goes beyond simple reinforcement theory accounts and suggests possible explanations for how peers may motivate adolescent behavior. PMID:24550063

Adolescent-specific patterns of behavior and neural activity during social reinforcement learning.

PubMed

Jones, Rebecca M; Somerville, Leah H; Li, Jian; Ruberry, Erika J; Powers, Alisa; Mehta, Natasha; Dyke, Jonathan; Casey, B J

2014-06-01

Humans are sophisticated social beings. Social cues from others are exceptionally salient, particularly during adolescence. Understanding how adolescents interpret and learn from variable social signals can provide insight into the observed shift in social sensitivity during this period. The present study tested 120 participants between the ages of 8 and 25 years on a social reinforcement learning task where the probability of receiving positive social feedback was parametrically manipulated. Seventy-eight of these participants completed the task during fMRI scanning. Modeling trial-by-trial learning, children and adults showed higher positive learning rates than did adolescents, suggesting that adolescents demonstrated less differentiation in their reaction times for peers who provided more positive feedback. Forming expectations about receiving positive social reinforcement correlated with neural activity within the medial prefrontal cortex and ventral striatum across age. Adolescents, unlike children and adults, showed greater insular activity during positive prediction error learning and increased activity in the supplementary motor cortex and the putamen when receiving positive social feedback regardless of the expected outcome, suggesting that peer approval may motivate adolescents toward action. While different amounts of positive social reinforcement enhanced learning in children and adults, all positive social reinforcement equally motivated adolescents. Together, these findings indicate that sensitivity to peer approval during adolescence goes beyond simple reinforcement theory accounts and suggest possible explanations for how peers may motivate adolescent behavior.

A reward optimization method based on action subrewards in hierarchical reinforcement learning.

PubMed

Fu, Yuchen; Liu, Quan; Ling, Xionghong; Cui, Zhiming

2014-01-01

Reinforcement learning (RL) is one kind of interactive learning methods. Its main characteristics are "trial and error" and "related reward." A hierarchical reinforcement learning method based on action subrewards is proposed to solve the problem of "curse of dimensionality," which means that the states space will grow exponentially in the number of features and low convergence speed. The method can reduce state spaces greatly and choose actions with favorable purpose and efficiency so as to optimize reward function and enhance convergence speed. Apply it to the online learning in Tetris game, and the experiment result shows that the convergence speed of this algorithm can be enhanced evidently based on the new method which combines hierarchical reinforcement learning algorithm and action subrewards. The "curse of dimensionality" problem is also solved to a certain extent with hierarchical method. All the performance with different parameters is compared and analyzed as well.

Reinforcement learning improves behaviour from evaluative feedback

NASA Astrophysics Data System (ADS)

Littman, Michael L.

2015-05-01

Reinforcement learning is a branch of machine learning concerned with using experience gained through interacting with the world and evaluative feedback to improve a system's ability to make behavioural decisions. It has been called the artificial intelligence problem in a microcosm because learning algorithms must act autonomously to perform well and achieve their goals. Partly driven by the increasing availability of rich data, recent years have seen exciting advances in the theory and practice of reinforcement learning, including developments in fundamental technical areas such as generalization, planning, exploration and empirical methodology, leading to increasing applicability to real-life problems.

Reinforcement learning improves behaviour from evaluative feedback.

PubMed

Littman, Michael L

2015-05-28

Reinforcement learning is a branch of machine learning concerned with using experience gained through interacting with the world and evaluative feedback to improve a system's ability to make behavioural decisions. It has been called the artificial intelligence problem in a microcosm because learning algorithms must act autonomously to perform well and achieve their goals. Partly driven by the increasing availability of rich data, recent years have seen exciting advances in the theory and practice of reinforcement learning, including developments in fundamental technical areas such as generalization, planning, exploration and empirical methodology, leading to increasing applicability to real-life problems.

Statistical mechanics of competitive resource allocation using agent-based models

NASA Astrophysics Data System (ADS)

Chakraborti, Anirban; Challet, Damien; Chatterjee, Arnab; Marsili, Matteo; Zhang, Yi-Cheng; Chakrabarti, Bikas K.

2015-01-01

Demand outstrips available resources in most situations, which gives rise to competition, interaction and learning. In this article, we review a broad spectrum of multi-agent models of competition (El Farol Bar problem, Minority Game, Kolkata Paise Restaurant problem, Stable marriage problem, Parking space problem and others) and the methods used to understand them analytically. We emphasize the power of concepts and tools from statistical mechanics to understand and explain fully collective phenomena such as phase transitions and long memory, and the mapping between agent heterogeneity and physical disorder. As these methods can be applied to any large-scale model of competitive resource allocation made up of heterogeneous adaptive agent with non-linear interaction, they provide a prospective unifying paradigm for many scientific disciplines.

Reinforcement learning controller design for affine nonlinear discrete-time systems using online approximators.

PubMed

Yang, Qinmin; Jagannathan, Sarangapani

2012-04-01

In this paper, reinforcement learning state- and output-feedback-based adaptive critic controller designs are proposed by using the online approximators (OLAs) for a general multi-input and multioutput affine unknown nonlinear discretetime systems in the presence of bounded disturbances. The proposed controller design has two entities, an action network that is designed to produce optimal signal and a critic network that evaluates the performance of the action network. The critic estimates the cost-to-go function which is tuned online using recursive equations derived from heuristic dynamic programming. Here, neural networks (NNs) are used both for the action and critic whereas any OLAs, such as radial basis functions, splines, fuzzy logic, etc., can be utilized. For the output-feedback counterpart, an additional NN is designated as the observer to estimate the unavailable system states, and thus, separation principle is not required. The NN weight tuning laws for the controller schemes are also derived while ensuring uniform ultimate boundedness of the closed-loop system using Lyapunov theory. Finally, the effectiveness of the two controllers is tested in simulation on a pendulum balancing system and a two-link robotic arm system.

Quantum-Enhanced Machine Learning

NASA Astrophysics Data System (ADS)

Dunjko, Vedran; Taylor, Jacob M.; Briegel, Hans J.

2016-09-01

The emerging field of quantum machine learning has the potential to substantially aid in the problems and scope of artificial intelligence. This is only enhanced by recent successes in the field of classical machine learning. In this work we propose an approach for the systematic treatment of machine learning, from the perspective of quantum information. Our approach is general and covers all three main branches of machine learning: supervised, unsupervised, and reinforcement learning. While quantum improvements in supervised and unsupervised learning have been reported, reinforcement learning has received much less attention. Within our approach, we tackle the problem of quantum enhancements in reinforcement learning as well, and propose a systematic scheme for providing improvements. As an example, we show that quadratic improvements in learning efficiency, and exponential improvements in performance over limited time periods, can be obtained for a broad class of learning problems.

The drift diffusion model as the choice rule in reinforcement learning.

PubMed

Pedersen, Mads Lund; Frank, Michael J; Biele, Guido

2017-08-01

Current reinforcement-learning models often assume simplified decision processes that do not fully reflect the dynamic complexities of choice processes. Conversely, sequential-sampling models of decision making account for both choice accuracy and response time, but assume that decisions are based on static decision values. To combine these two computational models of decision making and learning, we implemented reinforcement-learning models in which the drift diffusion model describes the choice process, thereby capturing both within- and across-trial dynamics. To exemplify the utility of this approach, we quantitatively fit data from a common reinforcement-learning paradigm using hierarchical Bayesian parameter estimation, and compared model variants to determine whether they could capture the effects of stimulant medication in adult patients with attention-deficit hyperactivity disorder (ADHD). The model with the best relative fit provided a good description of the learning process, choices, and response times. A parameter recovery experiment showed that the hierarchical Bayesian modeling approach enabled accurate estimation of the model parameters. The model approach described here, using simultaneous estimation of reinforcement-learning and drift diffusion model parameters, shows promise for revealing new insights into the cognitive and neural mechanisms of learning and decision making, as well as the alteration of such processes in clinical groups.

Can model-free reinforcement learning explain deontological moral judgments?

PubMed

Ayars, Alisabeth

2016-05-01

Dual-systems frameworks propose that moral judgments are derived from both an immediate emotional response, and controlled/rational cognition. Recently Cushman (2013) proposed a new dual-system theory based on model-free and model-based reinforcement learning. Model-free learning attaches values to actions based on their history of reward and punishment, and explains some deontological, non-utilitarian judgments. Model-based learning involves the construction of a causal model of the world and allows for far-sighted planning; this form of learning fits well with utilitarian considerations that seek to maximize certain kinds of outcomes. I present three concerns regarding the use of model-free reinforcement learning to explain deontological moral judgment. First, many actions that humans find aversive from model-free learning are not judged to be morally wrong. Moral judgment must require something in addition to model-free learning. Second, there is a dearth of evidence for central predictions of the reinforcement account-e.g., that people with different reinforcement histories will, all else equal, make different moral judgments. Finally, to account for the effect of intention within the framework requires certain assumptions which lack support. These challenges are reasonable foci for future empirical/theoretical work on the model-free/model-based framework. Copyright © 2016 Elsevier B.V. All rights reserved.

The drift diffusion model as the choice rule in reinforcement learning

PubMed Central

Frank, Michael J.

2017-01-01

Current reinforcement-learning models often assume simplified decision processes that do not fully reflect the dynamic complexities of choice processes. Conversely, sequential-sampling models of decision making account for both choice accuracy and response time, but assume that decisions are based on static decision values. To combine these two computational models of decision making and learning, we implemented reinforcement-learning models in which the drift diffusion model describes the choice process, thereby capturing both within- and across-trial dynamics. To exemplify the utility of this approach, we quantitatively fit data from a common reinforcement-learning paradigm using hierarchical Bayesian parameter estimation, and compared model variants to determine whether they could capture the effects of stimulant medication in adult patients with attention-deficit hyper-activity disorder (ADHD). The model with the best relative fit provided a good description of the learning process, choices, and response times. A parameter recovery experiment showed that the hierarchical Bayesian modeling approach enabled accurate estimation of the model parameters. The model approach described here, using simultaneous estimation of reinforcement-learning and drift diffusion model parameters, shows promise for revealing new insights into the cognitive and neural mechanisms of learning and decision making, as well as the alteration of such processes in clinical groups. PMID:27966103

General functioning predicts reward and punishment learning in schizophrenia.

PubMed

Somlai, Zsuzsanna; Moustafa, Ahmed A; Kéri, Szabolcs; Myers, Catherine E; Gluck, Mark A

2011-04-01

Previous studies investigating feedback-driven reinforcement learning in patients with schizophrenia have provided mixed results. In this study, we explored the clinical predictors of reward and punishment learning using a probabilistic classification learning task. Patients with schizophrenia (n=40) performed similarly to healthy controls (n=30) on the classification learning task. However, more severe negative and general symptoms were associated with lower reward-learning performance, whereas poorer general psychosocial functioning was correlated with both lower reward- and punishment-learning performances. Multiple linear regression analyses indicated that general psychosocial functioning was the only significant predictor of reinforcement learning performance when education, antipsychotic dose, and positive, negative and general symptoms were included in the analysis. These results suggest a close relationship between reinforcement learning and general psychosocial functioning in schizophrenia. Published by Elsevier B.V.

Distributed adaptive neural network control for a class of heterogeneous nonlinear multi-agent systems subject to actuation failures

NASA Astrophysics Data System (ADS)

Cui, Bing; Zhao, Chunhui; Ma, Tiedong; Feng, Chi

2017-02-01

In this paper, the cooperative adaptive consensus tracking problem for heterogeneous nonlinear multi-agent systems on directed graph is addressed. Each follower is modelled as a general nonlinear system with the unknown and nonidentical nonlinear dynamics, disturbances and actuator failures. Cooperative fault tolerant neural network tracking controllers with online adaptive learning features are proposed to guarantee that all agents synchronise to the trajectory of one leader with bounded adjustable synchronisation errors. With the help of linear quadratic regulator-based optimal design, a graph-dependent Lyapunov proof provides error bounds that depend on the graph topology, one virtual matrix and some design parameters. Of particular interest is that if the control gain is selected appropriately, the proposed control scheme can be implemented in a unified framework no matter whether there are faults or not. Furthermore, the fault detection and isolation are not needed to implement. Finally, a simulation is given to verify the effectiveness of the proposed method.

Operant conditioning of enhanced pain sensitivity by heat-pain titration.

PubMed

Becker, Susanne; Kleinböhl, Dieter; Klossika, Iris; Hölzl, Rupert

2008-11-15

Operant conditioning mechanisms have been demonstrated to be important in the development of chronic pain. Most experimental studies have investigated the operant modulation of verbal pain reports with extrinsic reinforcement, such as verbal reinforcement. Whether this reflects actual changes in the subjective experience of the nociceptive stimulus remained unclear. This study replicates and extends our previous demonstration that enhanced pain sensitivity to prolonged heat-pain stimulation could be learned in healthy participants through intrinsic reinforcement (contingent changes in nociceptive input) independent of verbal pain reports. In addition, we examine whether different magnitudes of reinforcement differentially enhance pain sensitivity using an operant heat-pain titration paradigm. It is based on the previously developed non-verbal behavioral discrimination task for the assessment of sensitization, which uses discriminative down- or up-regulation of stimulus temperatures in response to changes in subjective intensity. In operant heat-pain titration, this discriminative behavior and not verbal pain report was contingently reinforced or punished by acute decreases or increases in heat-pain intensity. The magnitude of reinforcement was varied between three groups: low (N1=13), medium (N2=11) and high reinforcement (N3=12). Continuous reinforcement was applied to acquire and train the operant behavior, followed by partial reinforcement to analyze the underlying learning mechanisms. Results demonstrated that sensitization to prolonged heat-pain stimulation was enhanced by operant learning within 1h. The extent of sensitization was directly dependent on the received magnitude of reinforcement. Thus, operant learning mechanisms based on intrinsic reinforcement may provide an explanation for the gradual development of sustained hypersensitivity during pain that is becoming chronic.

Predictors of return rate discrimination in slot machine play.

PubMed

Coates, Ewan; Blaszczynski, Alex

2014-09-01

The purpose of this study was to investigate the extent to which accurate estimates of payback percentages and volatility combined with prior learning, enabled players to successfully discriminate between multi-line/multi-credit slot machines that provided differing rates of reinforcement. The aim was to determine if the capacity to discriminate structural characteristics of gaming machines influenced player choices in selecting 'favourite' slot machines. Slot machine gambling history, gambling beliefs and knowledge, impulsivity, illusions of control, and problem solving style were assessed in a sample of 48 first year undergraduate psychology students. Participants were subsequently exposed to a choice paradigm where they could freely select to play either of two concurrently presented PC-simulated slot machines programmed to randomly differ in expected player return rates (payback percentage) and win frequency (volatility). Results suggest that prior learning and cognitions (particularly gambler's fallacy) but not payback, were major contributors to the ability of a player to discriminate volatility between slot machines. Participants displayed a general tendency to discriminate payback, but counter-intuitively placed more bets on the slot machine with lower payback percentage rates.

Dopamine-Dependent Reinforcement of Motor Skill Learning: Evidence from Gilles de la Tourette Syndrome

ERIC Educational Resources Information Center

Palminteri, Stefano; Lebreton, Mael; Worbe, Yulia; Hartmann, Andreas; Lehericy, Stephane; Vidailhet, Marie; Grabli, David; Pessiglione, Mathias

2011-01-01

Reinforcement learning theory has been extensively used to understand the neural underpinnings of instrumental behaviour. A central assumption surrounds dopamine signalling reward prediction errors, so as to update action values and ensure better choices in the future. However, educators may share the intuitive idea that reinforcements not only…

Preparing culture change agents for academic medicine in a multi-institutional consortium: the C - change learning action network.

PubMed

Pololi, Linda H; Krupat, Edward; Schnell, Eugene R; Kern, David E

2013-01-01

Research suggests an ongoing need for change in the culture of academic medicine. This article describes the structure, activities and evaluation of a culture change project: the C - Change Learning Action Network (LAN) and its impact on participants. The LAN was developed to create the experience of a culture that would prepare participants to facilitate a culture in academic medicine that would be more collaborative, inclusive, relational, and that supports the humanity and vitality of faculty. Purposefully diverse faculty, leaders, and deans from 5 US medical schools convened in 2 1/2-day meetings biannually over 4 years. LAN meetings employed experiential, cognitive, and affective learning modes; innovative dialogue strategies; and reflective practice aimed at facilitating deep dialogue, relationship formation, collaboration, authenticity, and transformative learning to help members experience the desired culture. Robust aggregated qualitative and quantitative data collected from the 5 schools were used to inform and stimulate culture-change plans. Quantitative and qualitative evaluation methods were used. Participants indicated that a safe, supportive, inclusive, collaborative culture was established in LAN and highly valued. LAN members reported a deepened understanding of organizational change, new and valued interpersonal connections, increased motivation and resilience, new skills and approaches, increased self-awareness and personal growth, emotional connection to the issues of diversity and inclusion, and application of new learnings in their work. A carefully designed multi-institutional learning community can transform the way participants experience and view institutional culture. It can motivate and prepare them to be change agents in their own institutions. Copyright © 2013 The Alliance for Continuing Education in the Health Professions, the Society for Academic Continuing Medical Education, and the Council on CME, Association for Hospital Medical Education.

Reinforcement and inference in cross-situational word learning.

PubMed

Tilles, Paulo F C; Fontanari, José F

2013-01-01

Cross-situational word learning is based on the notion that a learner can determine the referent of a word by finding something in common across many observed uses of that word. Here we propose an adaptive learning algorithm that contains a parameter that controls the strength of the reinforcement applied to associations between concurrent words and referents, and a parameter that regulates inference, which includes built-in biases, such as mutual exclusivity, and information of past learning events. By adjusting these parameters so that the model predictions agree with data from representative experiments on cross-situational word learning, we were able to explain the learning strategies adopted by the participants of those experiments in terms of a trade-off between reinforcement and inference. These strategies can vary wildly depending on the conditions of the experiments. For instance, for fast mapping experiments (i.e., the correct referent could, in principle, be inferred in a single observation) inference is prevalent, whereas for segregated contextual diversity experiments (i.e., the referents are separated in groups and are exhibited with members of their groups only) reinforcement is predominant. Other experiments are explained with more balanced doses of reinforcement and inference.

Learned helplessness and learned prevalence: exploring the causal relations among perceived controllability, reward prevalence, and exploration.

PubMed

Teodorescu, Kinneret; Erev, Ido

2014-10-01

Exposure to uncontrollable outcomes has been found to trigger learned helplessness, a state in which the agent, because of lack of exploration, fails to take advantage of regained control. Although the implications of this phenomenon have been widely studied, its underlying cause remains undetermined. One can learn not to explore because the environment is uncontrollable, because the average reinforcement for exploring is low, or because rewards for exploring are rare. In the current research, we tested a simple experimental paradigm that contrasts the predictions of these three contributors and offers a unified psychological mechanism that underlies the observed phenomena. Our results demonstrate that learned helplessness is not correlated with either the perceived controllability of one's environment or the average reward, which suggests that reward prevalence is a better predictor of exploratory behavior than the other two factors. A simple computational model in which exploration decisions were based on small samples of past experiences captured the empirical phenomena while also providing a cognitive basis for feelings of uncontrollability. © The Author(s) 2014.

Overcoming Learned Helplessness in Community College Students.

ERIC Educational Resources Information Center

Roueche, John E.; Mink, Oscar G.

1982-01-01

Reviews research on the effects of repeated experiences of helplessness and on locus of control. Identifies conditions necessary for overcoming learned helplessness; i.e., the potential for learning to occur; consistent reinforcement; relevant, valued reinforcers; and favorable psychological situation. Recommends eight ways for teachers to…

Dopamine D2 Receptor Signaling in the Nucleus Accumbens Comprises a Metabolic-Cognitive Brain Interface Regulating Metabolic Components of Glucose Reinforcement.

PubMed

Michaelides, Michael; Miller, Michael L; DiNieri, Jennifer A; Gomez, Juan L; Schwartz, Elizabeth; Egervari, Gabor; Wang, Gene Jack; Mobbs, Charles V; Volkow, Nora D; Hurd, Yasmin L

2017-11-01

Appetitive drive is influenced by coordinated interactions between brain circuits that regulate reinforcement and homeostatic signals that control metabolism. Glucose modulates striatal dopamine (DA) and regulates appetitive drive and reinforcement learning. Striatal DA D2 receptors (D2Rs) also regulate reinforcement learning and are implicated in glucose-related metabolic disorders. Nevertheless, interactions between striatal D2R and peripheral glucose have not been previously described. Here we show that manipulations involving striatal D2R signaling coincide with perseverative and impulsive-like responding for sucrose, a disaccharide consisting of fructose and glucose. Fructose conveys orosensory (ie, taste) reinforcement but does not convey metabolic (ie, nutrient-derived) reinforcement. Glucose however conveys orosensory reinforcement but unlike fructose, it is a major metabolic energy source, underlies sustained reinforcement, and activates striatal circuitry. We found that mice with deletion of dopamine- and cAMP-regulated neuronal phosphoprotein (DARPP-32) exclusively in D2R-expressing cells exhibited preferential D2R changes in the nucleus accumbens (NAc), a striatal region that critically regulates sucrose reinforcement. These changes coincided with perseverative and impulsive-like responding for sucrose pellets and sustained reinforcement learning of glucose-paired flavors. These mice were also characterized by significant glucose intolerance (ie, impaired glucose utilization). Systemic glucose administration significantly attenuated sucrose operant responding and D2R activation or blockade in the NAc bidirectionally modulated blood glucose levels and glucose tolerance. Collectively, these results implicate NAc D2R in regulating both peripheral glucose levels and glucose-dependent reinforcement learning behaviors and highlight the notion that glucose metabolic impairments arising from disrupted NAc D2R signaling are involved in compulsive and perseverative feeding behaviors.

Learning what matters: A neural explanation for the sparsity bias.

PubMed

Hassall, Cameron D; Connor, Patrick C; Trappenberg, Thomas P; McDonald, John J; Krigolson, Olave E

2018-05-01

The visual environment is filled with complex, multi-dimensional objects that vary in their value to an observer's current goals. When faced with multi-dimensional stimuli, humans may rely on biases to learn to select those objects that are most valuable to the task at hand. Here, we show that decision making in a complex task is guided by the sparsity bias: the focusing of attention on a subset of available features. Participants completed a gambling task in which they selected complex stimuli that varied randomly along three dimensions: shape, color, and texture. Each dimension comprised three features (e.g., color: red, green, yellow). Only one dimension was relevant in each block (e.g., color), and a randomly-chosen value ranking determined outcome probabilities (e.g., green > yellow > red). Participants were faster to respond to infrequent probe stimuli that appeared unexpectedly within stimuli that possessed a more valuable feature than to probes appearing within stimuli possessing a less valuable feature. Event-related brain potentials recorded during the task provided a neurophysiological explanation for sparsity as a learning-dependent increase in optimal attentional performance (as measured by the N2pc component of the human event-related potential) and a concomitant learning-dependent decrease in prediction errors (as measured by the feedback-elicited reward positivity). Together, our results suggest that the sparsity bias guides human reinforcement learning in complex environments. Copyright © 2018 Elsevier B.V. All rights reserved.

Acquisition of Autonomous Behaviors by Robotic Assistants

NASA Technical Reports Server (NTRS)

Peters, R. A., II; Sarkar, N.; Bodenheimer, R. E.; Brown, E.; Campbell, C.; Hambuchen, K.; Johnson, C.; Koku, A. B.; Nilas, P.; Peng, J.

2005-01-01

Our research achievements under the NASA-JSC grant contributed significantly in the following areas. Multi-agent based robot control architecture called the Intelligent Machine Architecture (IMA) : The Vanderbilt team received a Space Act Award for this research from NASA JSC in October 2004. Cognitive Control and the Self Agent : Cognitive control in human is the ability to consciously manipulate thoughts and behaviors using attention to deal with conflicting goals and demands. We have been updating the IMA Self Agent towards this goal. If opportunity arises, we would like to work with NASA to empower Robonaut to do cognitive control. Applications 1. SES for Robonaut, 2. Robonaut Fault Diagnostic System, 3. ISAC Behavior Generation and Learning, 4. Segway Research.

Applications of Multi-Agent Technology to Power Systems

NASA Astrophysics Data System (ADS)

Nagata, Takeshi

Currently, agents are focus of intense on many sub-fields of computer science and artificial intelligence. Agents are being used in an increasingly wide variety of applications. Many important computing applications such as planning, process control, communication networks and concurrent systems will benefit from using multi-agent system approach. A multi-agent system is a structure given by an environment together with a set of artificial agents capable to act on this environment. Multi-agent models are oriented towards interactions, collaborative phenomena, and autonomy. This article presents the applications of multi-agent technology to the power systems.

Push-out bond strengths of two fiber post types bonded with different dentin bonding agents.

PubMed

Topcu, Fulya Toksoy; Erdemir, Ugur; Sahinkesen, Gunes; Mumcu, Emre; Yildiz, Esra; Uslan, Ibrahim

2010-05-01

The aim of this study was to evaluate the regional push-out bond strengths for two fiber-reinforced post types using three different dentin bonding agents. Sixty single-rooted extracted human first premolar teeth were sectioned below the cemento-enamel junction, and the roots were endodontically treated. Following standardized post space preparations, the roots were divided into two fiber-post groups (Glassix and Carbopost), and further divided into three subgroups of 10 specimens each for the bonding systems self-etching dentin bonding agents (Clearfil SE Bond and Optibond all-in-one), and total-etching dentin bonding agent (XP Bond). A dual-cure resin luting cement (Maxcem) was then placed in the post spaces and posts were then seated into the root canals polymerized through the cervical portion. The roots were then cut into 3-mm thick sections. Push-out tests were performed at a crosshead speed of 0.5 mm/min. The data were analyzed with multivariate ANOVA (alpha = 0.05). The morphology of interface between different dentin bonding agents from the cervical sections were analyzed with SEM. Glass fiber-reinforced posts demonstrated significantly higher push-out bond strengths than carbon fiber-reinforced posts (p < 0.001). Bond strength values decreased significantly from the cervical to the apical root canal regions (p < 0.001). Self-etching dentin adhesive Clearfil SE Bond and total-etching dentin adhesive XP Bond demonstrated similar bond strengths values and this was significantly higher compared with the Optibond all-in-one in cervical root canal region. In conclusion, in all root segments, the glass fiber-reinforced posts provided significantly increased post retention than the carbon fiber-reinforced posts, regardless of the adhesive used. (c) 2010 Wiley Periodicals, Inc.

The Effects of Partial Reinforcement in the Acquisition and Extinction of Recurrent Serial Patterns.

ERIC Educational Resources Information Center

Dockstader, Steven L.

The purpose of these 2 experiments was to determine whether sequential response pattern behavior is affected by partial reinforcement in the same way as other behavior systems. The first experiment investigated the partial reinforcement extinction effects (PREE) in a sequential concept learning task where subjects were required to learn a…

Microstimulation of the Human Substantia Nigra Alters Reinforcement Learning

PubMed Central

Ramayya, Ashwin G.; Misra, Amrit

2014-01-01

Animal studies have shown that substantia nigra (SN) dopaminergic (DA) neurons strengthen action–reward associations during reinforcement learning, but their role in human learning is not known. Here, we applied microstimulation in the SN of 11 patients undergoing deep brain stimulation surgery for the treatment of Parkinson's disease as they performed a two-alternative probability learning task in which rewards were contingent on stimuli, rather than actions. Subjects demonstrated decreased learning from reward trials that were accompanied by phasic SN microstimulation compared with reward trials without stimulation. Subjects who showed large decreases in learning also showed an increased bias toward repeating actions after stimulation trials; therefore, stimulation may have decreased learning by strengthening action–reward associations rather than stimulus–reward associations. Our findings build on previous studies implicating SN DA neurons in preferentially strengthening action–reward associations during reinforcement learning. PMID:24828643

An Investigation of Ways to Reduce the Failure Rate of Student Pilots during Flying Training in the Royal Australian Air Force.

DTIC Science & Technology

1987-09-01

Luthans (28) expanded the concept of learning as follows: 1. Learning involves a change, though not necessarily an improvement, in behaviour. Learning...that results in an unpleasant outcome is not likely to be repeated (36:244). Luthans and Kreitner (27) described the various forms of reinforcement as...four 33 alternatives (defined previously on page 24 and taken from Luthans ) of positive reinforcement, negative reinforcement, extinction and punishment

Comparative Studies on Al-Based Composite Powder Reinforced with Nano Garnet and Multi-wall Carbon Nanotubes

NASA Astrophysics Data System (ADS)

Basariya, M. Raviathul; Srivastava, V. C.; Mukhopadhyay, N. K.

2015-11-01

Effect of mechanical alloying/milling on microstructural evolution and hardness variations of garnet and multi-walled carbon nanotubes (MWCNTs)-reinforced Al-Mg-Si alloy (EN AW6082) composites are investigated. Structural and morphological studies revealed that the composite powders prepared by milling display a more homogenous distribution of the reinforcing particles. Improved nanoindentation hardness viz., 4.24 and 5.90 GPa are achieved for EN AW6082/Garnet and EN AW6082/MWCNTs composites, respectively, and it is attributed to severe deformation of the aluminum alloy powders and embedding of the harder reinforcement particles uniformly into the aluminum alloy matrix. However, enhancement in case of MWCNTs-reinforced composite makes apparent the effect of its nanosized uniform dispersion in the matrix, thereby resisting the plastic deformation at lower stress and increased dislocation density evolved during high-energy ball milling. The results of the present study indicate that carbon nanotubes and garnet can be effectively used as reinforcements for Al-based composites.

Mastery Learning through Individualized Instruction: A Reinforcement Strategy

ERIC Educational Resources Information Center

Sagy, John; Ravi, R.; Ananthasayanam, R.

2009-01-01

The present study attempts to gauge the effect of individualized instructional methods as a reinforcement strategy for mastery learning. Among various individualized instructional methods, the study focuses on PIM (Programmed Instructional Method) and CAIM (Computer Assisted Instruction Method). Mastery learning is a process where students achieve…

Working Memory and Reinforcement Schedule Jointly Determine Reinforcement Learning in Children: Potential Implications for Behavioral Parent Training

PubMed Central

Segers, Elien; Beckers, Tom; Geurts, Hilde; Claes, Laurence; Danckaerts, Marina; van der Oord, Saskia

2018-01-01

Introduction: Behavioral Parent Training (BPT) is often provided for childhood psychiatric disorders. These disorders have been shown to be associated with working memory impairments. BPT is based on operant learning principles, yet how operant principles shape behavior (through the partial reinforcement (PRF) extinction effect, i.e., greater resistance to extinction that is created when behavior is reinforced partially rather than continuously) and the potential role of working memory therein is scarcely studied in children. This study explored the PRF extinction effect and the role of working memory therein using experimental tasks in typically developing children. Methods: Ninety-seven children (age 6–10) completed a working memory task and an operant learning task, in which children acquired a response-sequence rule under either continuous or PRF (120 trials), followed by an extinction phase (80 trials). Data of 88 children were used for analysis. Results: The PRF extinction effect was confirmed: We observed slower acquisition and extinction in the PRF condition as compared to the continuous reinforcement (CRF) condition. Working memory was negatively related to acquisition but not extinction performance. Conclusion: Both reinforcement contingencies and working memory relate to acquisition performance. Potential implications for BPT are that decreasing working memory load may enhance the chance of optimally learning through reinforcement. PMID:29643822

The learner's perspective in GP teaching practices with multi-level learners: a qualitative study.

PubMed

Thomson, Jennifer S; Anderson, Katrina; Haesler, Emily; Barnard, Amanda; Glasgow, Nicholas

2014-03-19

Medical students, junior hospital doctors on rotation and general practice (GP) registrars are undertaking their training in clinical general practices in increasing numbers in Australia. Some practices have four levels of learner. This study aimed to explore how multi-level teaching (also called vertical integration of GP education and training) is occurring in clinical general practice and the impact of such teaching on the learner. A qualitative research methodology was used with face-to-face, semi-structured interviews of medical students, junior hospital doctors, GP registrars and GP teachers in eight training practices in the region that taught all levels of learners. Interviews were audio-recorded and transcribed. Qualitative analysis was conducted using thematic analysis techniques aided by the use of the software package N-Vivo 9. Primary themes were identified and categorised by the co-investigators. 52 interviews were completed and analysed. Themes were identified relating to both the practice learning environment and teaching methods used.A practice environment where there is a strong teaching culture, enjoyment of learning, and flexible learning methods, as well as learning spaces and organised teaching arrangements, all contribute to positive learning from a learners' perspective.Learners identified a number of innovative teaching methods and viewed them as positive. These included multi-level learner group tutorials in the practice, being taught by a team of teachers, including GP registrars and other health professionals, and access to a supernumerary GP supervisor (also termed "GP consultant teacher"). Other teaching methods that were viewed positively were parallel consulting, informal learning and rural hospital context integrated learning. Vertical integration of GP education and training generally impacted positively on all levels of learner. This research has provided further evidence about the learning culture, structures and teaching processes that have a positive impact on learners in the clinical general practice setting where there are multiple levels of learners. It has also identified some innovative teaching methods that will need further examination. The findings reinforce the importance of the environment for learning and learner centred approaches and will be important for training organisations developing vertically integrated practices and in their training of GP teachers.

The learner’s perspective in GP teaching practices with multi-level learners: a qualitative study

PubMed Central

2014-01-01

Background Medical students, junior hospital doctors on rotation and general practice (GP) registrars are undertaking their training in clinical general practices in increasing numbers in Australia. Some practices have four levels of learner. This study aimed to explore how multi-level teaching (also called vertical integration of GP education and training) is occurring in clinical general practice and the impact of such teaching on the learner. Methods A qualitative research methodology was used with face-to-face, semi-structured interviews of medical students, junior hospital doctors, GP registrars and GP teachers in eight training practices in the region that taught all levels of learners. Interviews were audio-recorded and transcribed. Qualitative analysis was conducted using thematic analysis techniques aided by the use of the software package N-Vivo 9. Primary themes were identified and categorised by the co-investigators. Results 52 interviews were completed and analysed. Themes were identified relating to both the practice learning environment and teaching methods used. A practice environment where there is a strong teaching culture, enjoyment of learning, and flexible learning methods, as well as learning spaces and organised teaching arrangements, all contribute to positive learning from a learners’ perspective. Learners identified a number of innovative teaching methods and viewed them as positive. These included multi-level learner group tutorials in the practice, being taught by a team of teachers, including GP registrars and other health professionals, and access to a supernumerary GP supervisor (also termed “GP consultant teacher”). Other teaching methods that were viewed positively were parallel consulting, informal learning and rural hospital context integrated learning. Conclusions Vertical integration of GP education and training generally impacted positively on all levels of learner. This research has provided further evidence about the learning culture, structures and teaching processes that have a positive impact on learners in the clinical general practice setting where there are multiple levels of learners. It has also identified some innovative teaching methods that will need further examination. The findings reinforce the importance of the environment for learning and learner centred approaches and will be important for training organisations developing vertically integrated practices and in their training of GP teachers. PMID:24645670

Instructional control of reinforcement learning: A behavioral and neurocomputational investigation

PubMed Central

Doll, Bradley B.; Jacobs, W. Jake; Sanfey, Alan G.; Frank, Michael J.

2011-01-01

Humans learn how to behave directly through environmental experience and indirectly through rules and instructions. Behavior analytic research has shown that instructions can control behavior, even when such behavior leads to sub-optimal outcomes (Hayes, S. (Ed.). 1989. Rule-governed behavior: cognition, contingencies, and instructional control. Plenum Press.). Here we examine the control of behavior through instructions in a reinforcement learning task known to depend on striatal dopaminergic function. Participants selected between probabilistically reinforced stimuli, and were (incorrectly) told that a specific stimulus had the highest (or lowest) reinforcement probability. Despite experience to the contrary, instructions drove choice behavior. We present neural network simulations that capture the interactions between instruction-driven and reinforcement-driven behavior via two potential neural circuits: one in which the striatum is inaccurately trained by instruction representations coming from prefrontal cortex/hippocampus (PFC/HC), and another in which the striatum learns the environmentally based reinforcement contingencies, but is “overridden” at decision output. Both models capture the core behavioral phenomena but, because they differ fundamentally on what is learned, make distinct predictions for subsequent behavioral and neuroimaging experiments. Finally, we attempt to distinguish between the proposed computational mechanisms governing instructed behavior by fitting a series of abstract “Q-learning” and Bayesian models to subject data. The best-fitting model supports one of the neural models, suggesting the existence of a “confirmation bias” in which the PFC/HC system trains the reinforcement system by amplifying outcomes that are consistent with instructions while diminishing inconsistent outcomes. PMID:19595993

How partial reinforcement of food cues affects the extinction and reacquisition of appetitive responses. A new model for dieting success?

PubMed

van den Akker, Karolien; Havermans, Remco C; Bouton, Mark E; Jansen, Anita

2014-10-01

Animals and humans can easily learn to associate an initially neutral cue with food intake through classical conditioning, but extinction of learned appetitive responses can be more difficult. Intermittent or partial reinforcement of food cues causes especially persistent behaviour in animals: after exposure to such learning schedules, the decline in responding that occurs during extinction is slow. After extinction, increases in responding with renewed reinforcement of food cues (reacquisition) might be less rapid after acquisition with partial reinforcement. In humans, it may be that the eating behaviour of some individuals resembles partial reinforcement schedules to a greater extent, possibly affecting dieting success by interacting with extinction and reacquisition. Furthermore, impulsivity has been associated with less successful dieting, and this association might be explained by impulsivity affecting the learning and extinction of appetitive responses. In the present two studies, the effects of different reinforcement schedules and impulsivity on the acquisition, extinction, and reacquisition of appetitive responses were investigated in a conditioning paradigm involving food rewards in healthy humans. Overall, the results indicate both partial reinforcement schedules and, possibly, impulsivity to be associated with worse extinction performance. A new model of dieting success is proposed: learning histories and, perhaps, certain personality traits (impulsivity) can interfere with the extinction and reacquisition of appetitive responses to food cues and they may be causally related to unsuccessful dieting. Copyright © 2014 Elsevier Ltd. All rights reserved.

Regulating recognition decisions through incremental reinforcement learning.

PubMed

Han, Sanghoon; Dobbins, Ian G

2009-06-01

Does incremental reinforcement learning influence recognition memory judgments? We examined this question by subtly altering the relative validity or availability of feedback in order to differentially reinforce old or new recognition judgments. Experiment 1 probabilistically and incorrectly indicated that either misses or false alarms were correct in the context of feedback that was otherwise accurate. Experiment 2 selectively withheld feedback for either misses or false alarms in the context of feedback that was otherwise present. Both manipulations caused prominent shifts of recognition memory decision criteria that remained for considerable periods even after feedback had been altogether removed. Overall, these data demonstrate that incremental reinforcement-learning mechanisms influence the degree of caution subjects exercise when evaluating explicit memories.

Infant Contingency Learning in Different Cultural Contexts

ERIC Educational Resources Information Center

Graf, Frauke; Lamm, Bettina; Goertz, Claudia; Kolling, Thorsten; Freitag, Claudia; Spangler, Sibylle; Fassbender, Ina; Teubert, Manuel; Vierhaus, Marc; Keller, Heidi; Lohaus, Arnold; Schwarzer, Gudrun; Knopf, Monika

2012-01-01

Three-month-old Cameroonian Nso farmer and German middle-class infants were compared regarding learning and retention in a computerized mobile task. Infants achieving a preset learning criterion during reinforcement were tested for immediate and long-term retention measured in terms of an increased response rate after reinforcement and after a…

Adaptive Educational Software by Applying Reinforcement Learning

ERIC Educational Resources Information Center

Bennane, Abdellah

2013-01-01

The introduction of the intelligence in teaching software is the object of this paper. In software elaboration process, one uses some learning techniques in order to adapt the teaching software to characteristics of student. Generally, one uses the artificial intelligence techniques like reinforcement learning, Bayesian network in order to adapt…

A Robust Cooperated Control Method with Reinforcement Learning and Adaptive H∞ Control

NASA Astrophysics Data System (ADS)

Obayashi, Masanao; Uchiyama, Shogo; Kuremoto, Takashi; Kobayashi, Kunikazu

This study proposes a robust cooperated control method combining reinforcement learning with robust control to control the system. A remarkable characteristic of the reinforcement learning is that it doesn't require model formula, however, it doesn't guarantee the stability of the system. On the other hand, robust control system guarantees stability and robustness, however, it requires model formula. We employ both the actor-critic method which is a kind of reinforcement learning with minimal amount of computation to control continuous valued actions and the traditional robust control, that is, H∞ control. The proposed system was compared method with the conventional control method, that is, the actor-critic only used, through the computer simulation of controlling the angle and the position of a crane system, and the simulation result showed the effectiveness of the proposed method.

The Enhancement of Composite Scarf Joint Interface Strength Through Carbon Nanotube Reinforcement

DTIC Science & Technology

2007-06-01

includes single walled carbon nanotubes (SWCNT) and multi-walled carbon nanotubes ( MWCNT ) with varying length, purity, and concentration levels along the...OF PAGES 106 14. SUBJECT TERMS Carbon Nanotubes, CNT, SWCNT, MWCNT , Bamboo, Polymer Composite, Joint Strength Enhancement, Reinforcement 16...variables concerning the carbon nanotube application. The testing includes single walled carbon nanotubes (SWCNT) and multi-walled carbon nanotubes ( MWCNT

Deep reinforcement learning for automated radiation adaptation in lung cancer.

PubMed

Tseng, Huan-Hsin; Luo, Yi; Cui, Sunan; Chien, Jen-Tzung; Ten Haken, Randall K; Naqa, Issam El

2017-12-01

To investigate deep reinforcement learning (DRL) based on historical treatment plans for developing automated radiation adaptation protocols for nonsmall cell lung cancer (NSCLC) patients that aim to maximize tumor local control at reduced rates of radiation pneumonitis grade 2 (RP2). In a retrospective population of 114 NSCLC patients who received radiotherapy, a three-component neural networks framework was developed for deep reinforcement learning (DRL) of dose fractionation adaptation. Large-scale patient characteristics included clinical, genetic, and imaging radiomics features in addition to tumor and lung dosimetric variables. First, a generative adversarial network (GAN) was employed to learn patient population characteristics necessary for DRL training from a relatively limited sample size. Second, a radiotherapy artificial environment (RAE) was reconstructed by a deep neural network (DNN) utilizing both original and synthetic data (by GAN) to estimate the transition probabilities for adaptation of personalized radiotherapy patients' treatment courses. Third, a deep Q-network (DQN) was applied to the RAE for choosing the optimal dose in a response-adapted treatment setting. This multicomponent reinforcement learning approach was benchmarked against real clinical decisions that were applied in an adaptive dose escalation clinical protocol. In which, 34 patients were treated based on avid PET signal in the tumor and constrained by a 17.2% normal tissue complication probability (NTCP) limit for RP2. The uncomplicated cure probability (P+) was used as a baseline reward function in the DRL. Taking our adaptive dose escalation protocol as a blueprint for the proposed DRL (GAN + RAE + DQN) architecture, we obtained an automated dose adaptation estimate for use at ∼2/3 of the way into the radiotherapy treatment course. By letting the DQN component freely control the estimated adaptive dose per fraction (ranging from 1-5 Gy), the DRL automatically favored dose escalation/de-escalation between 1.5 and 3.8 Gy, a range similar to that used in the clinical protocol. The same DQN yielded two patterns of dose escalation for the 34 test patients, but with different reward variants. First, using the baseline P+ reward function, individual adaptive fraction doses of the DQN had similar tendencies to the clinical data with an RMSE = 0.76 Gy; but adaptations suggested by the DQN were generally lower in magnitude (less aggressive). Second, by adjusting the P+ reward function with higher emphasis on mitigating local failure, better matching of doses between the DQN and the clinical protocol was achieved with an RMSE = 0.5 Gy. Moreover, the decisions selected by the DQN seemed to have better concordance with patients eventual outcomes. In comparison, the traditional temporal difference (TD) algorithm for reinforcement learning yielded an RMSE = 3.3 Gy due to numerical instabilities and lack of sufficient learning. We demonstrated that automated dose adaptation by DRL is a feasible and a promising approach for achieving similar results to those chosen by clinicians. The process may require customization of the reward function if individual cases were to be considered. However, development of this framework into a fully credible autonomous system for clinical decision support would require further validation on larger multi-institutional datasets. © 2017 American Association of Physicists in Medicine.

A spiking neural network model of model-free reinforcement learning with high-dimensional sensory input and perceptual ambiguity.

PubMed

Nakano, Takashi; Otsuka, Makoto; Yoshimoto, Junichiro; Doya, Kenji

2015-01-01

A theoretical framework of reinforcement learning plays an important role in understanding action selection in animals. Spiking neural networks provide a theoretically grounded means to test computational hypotheses on neurally plausible algorithms of reinforcement learning through numerical simulation. However, most of these models cannot handle observations which are noisy, or occurred in the past, even though these are inevitable and constraining features of learning in real environments. This class of problem is formally known as partially observable reinforcement learning (PORL) problems. It provides a generalization of reinforcement learning to partially observable domains. In addition, observations in the real world tend to be rich and high-dimensional. In this work, we use a spiking neural network model to approximate the free energy of a restricted Boltzmann machine and apply it to the solution of PORL problems with high-dimensional observations. Our spiking network model solves maze tasks with perceptually ambiguous high-dimensional observations without knowledge of the true environment. An extended model with working memory also solves history-dependent tasks. The way spiking neural networks handle PORL problems may provide a glimpse into the underlying laws of neural information processing which can only be discovered through such a top-down approach.

Punishment insensitivity and impaired reinforcement learning in preschoolers.

PubMed

Briggs-Gowan, Margaret J; Nichols, Sara R; Voss, Joel; Zobel, Elvira; Carter, Alice S; McCarthy, Kimberly J; Pine, Daniel S; Blair, James; Wakschlag, Lauren S

2014-01-01

Youth and adults with psychopathic traits display disrupted reinforcement learning. Advances in measurement now enable examination of this association in preschoolers. The current study examines relations between reinforcement learning in preschoolers and parent ratings of reduced responsiveness to socialization, conceptualized as a developmental vulnerability to psychopathic traits. One hundred and fifty-seven preschoolers (mean age 4.7 ± 0.8 years) participated in a substudy that was embedded within a larger project. Children completed the 'Stars-in-Jars' task, which involved learning to select rewarded jars and avoid punished jars. Maternal report of responsiveness to socialization was assessed with the Punishment Insensitivity and Low Concern for Others scales of the Multidimensional Assessment of Preschool Disruptive Behavior (MAP-DB). Punishment Insensitivity, but not Low Concern for Others, was significantly associated with reinforcement learning in multivariate models that accounted for age and sex. Specifically, higher Punishment Insensitivity was associated with significantly lower overall performance and more errors on punished trials ('passive avoidance'). Impairments in reinforcement learning manifest in preschoolers who are high in maternal ratings of Punishment Insensitivity. If replicated, these findings may help to pinpoint the neurodevelopmental antecedents of psychopathic tendencies and suggest novel intervention targets beginning in early childhood. © 2013 The Authors. Journal of Child Psychology and Psychiatry © 2013 Association for Child and Adolescent Mental Health.

A Spiking Neural Network Model of Model-Free Reinforcement Learning with High-Dimensional Sensory Input and Perceptual Ambiguity

PubMed Central

Nakano, Takashi; Otsuka, Makoto; Yoshimoto, Junichiro; Doya, Kenji

2015-01-01

A theoretical framework of reinforcement learning plays an important role in understanding action selection in animals. Spiking neural networks provide a theoretically grounded means to test computational hypotheses on neurally plausible algorithms of reinforcement learning through numerical simulation. However, most of these models cannot handle observations which are noisy, or occurred in the past, even though these are inevitable and constraining features of learning in real environments. This class of problem is formally known as partially observable reinforcement learning (PORL) problems. It provides a generalization of reinforcement learning to partially observable domains. In addition, observations in the real world tend to be rich and high-dimensional. In this work, we use a spiking neural network model to approximate the free energy of a restricted Boltzmann machine and apply it to the solution of PORL problems with high-dimensional observations. Our spiking network model solves maze tasks with perceptually ambiguous high-dimensional observations without knowledge of the true environment. An extended model with working memory also solves history-dependent tasks. The way spiking neural networks handle PORL problems may provide a glimpse into the underlying laws of neural information processing which can only be discovered through such a top-down approach. PMID:25734662

Rats bred for helplessness exhibit positive reinforcement learning deficits which are not alleviated by an antidepressant dose of the MAO-B inhibitor deprenyl.

PubMed

Schulz, Daniela; Henn, Fritz A; Petri, David; Huston, Joseph P

2016-08-04

Principles of negative reinforcement learning may play a critical role in the etiology and treatment of depression. We examined the integrity of positive reinforcement learning in congenitally helpless (cH) rats, an animal model of depression, using a random ratio schedule and a devaluation-extinction procedure. Furthermore, we tested whether an antidepressant dose of the monoamine oxidase (MAO)-B inhibitor deprenyl would reverse any deficits in positive reinforcement learning. We found that cH rats (n=9) were impaired in the acquisition of even simple operant contingencies, such as a fixed interval (FI) 20 schedule. cH rats exhibited no apparent deficits in appetite or reward sensitivity. They reacted to the devaluation of food in a manner consistent with a dose-response relationship. Reinforcer motivation as assessed by lever pressing across sessions with progressively decreasing reward probabilities was highest in congenitally non-helpless (cNH, n=10) rats as long as the reward probabilities remained relatively high. cNH compared to wild-type (n=10) rats were also more resistant to extinction across sessions. Compared to saline (n=5), deprenyl (n=5) reduced the duration of immobility of cH rats in the forced swimming test, indicative of antidepressant effects, but did not restore any deficits in the acquisition of a FI 20 schedule. We conclude that positive reinforcement learning was impaired in rats bred for helplessness, possibly due to motivational impairments but not deficits in reward sensitivity, and that deprenyl exerted antidepressant effects but did not reverse the deficits in positive reinforcement learning. Copyright © 2016 IBRO. Published by Elsevier Ltd. All rights reserved.

Antipsychotic dose modulates behavioral and neural responses to feedback during reinforcement learning in schizophrenia.

PubMed

Insel, Catherine; Reinen, Jenna; Weber, Jochen; Wager, Tor D; Jarskog, L Fredrik; Shohamy, Daphna; Smith, Edward E

2014-03-01

Schizophrenia is characterized by an abnormal dopamine system, and dopamine blockade is the primary mechanism of antipsychotic treatment. Consistent with the known role of dopamine in reward processing, prior research has demonstrated that patients with schizophrenia exhibit impairments in reward-based learning. However, it remains unknown how treatment with antipsychotic medication impacts the behavioral and neural signatures of reinforcement learning in schizophrenia. The goal of this study was to examine whether antipsychotic medication modulates behavioral and neural responses to prediction error coding during reinforcement learning. Patients with schizophrenia completed a reinforcement learning task while undergoing functional magnetic resonance imaging. The task consisted of two separate conditions in which participants accumulated monetary gain or avoided monetary loss. Behavioral results indicated that antipsychotic medication dose was associated with altered behavioral approaches to learning, such that patients taking higher doses of medication showed increased sensitivity to negative reinforcement. Higher doses of antipsychotic medication were also associated with higher learning rates (LRs), suggesting that medication enhanced sensitivity to trial-by-trial feedback. Neuroimaging data demonstrated that antipsychotic dose was related to differences in neural signatures of feedback prediction error during the loss condition. Specifically, patients taking higher doses of medication showed attenuated prediction error responses in the striatum and the medial prefrontal cortex. These findings indicate that antipsychotic medication treatment may influence motivational processes in patients with schizophrenia.

The Effects of Sensor Performance as Modeled by Signal Detection Theory on the Performance of Reinforcement Learning in a Target Acquisition Task

NASA Astrophysics Data System (ADS)

Quirion, Nate

Unmanned Aerial Systems (UASs) today are fulfilling more roles than ever before. There is a general push to have these systems feature more advanced autonomous capabilities in the near future. To achieve autonomous behavior requires some unique approaches to control and decision making. More advanced versions of these approaches are able to adapt their own behavior and examine their past experiences to increase their future mission performance. To achieve adaptive behavior and decision making capabilities this study used Reinforcement Learning algorithms. In this research the effects of sensor performance, as modeled through Signal Detection Theory (SDT), on the ability of RL algorithms to accomplish a target localization task are examined. Three levels of sensor sensitivity are simulated and compared to the results of the same system using a perfect sensor. To accomplish the target localization task, a hierarchical architecture used two distinct agents. A simulated human operator is assumed to be a perfect decision maker, and is used in the system feedback. An evaluation of the system is performed using multiple metrics, including episodic reward curves and the time taken to locate all targets. Statistical analyses are employed to detect significant differences in the comparison of steady-state behavior of different systems.

How we learn to make decisions: rapid propagation of reinforcement learning prediction errors in humans.

PubMed

Krigolson, Olav E; Hassall, Cameron D; Handy, Todd C

2014-03-01

Our ability to make decisions is predicated upon our knowledge of the outcomes of the actions available to us. Reinforcement learning theory posits that actions followed by a reward or punishment acquire value through the computation of prediction errors-discrepancies between the predicted and the actual reward. A multitude of neuroimaging studies have demonstrated that rewards and punishments evoke neural responses that appear to reflect reinforcement learning prediction errors [e.g., Krigolson, O. E., Pierce, L. J., Holroyd, C. B., & Tanaka, J. W. Learning to become an expert: Reinforcement learning and the acquisition of perceptual expertise. Journal of Cognitive Neuroscience, 21, 1833-1840, 2009; Bayer, H. M., & Glimcher, P. W. Midbrain dopamine neurons encode a quantitative reward prediction error signal. Neuron, 47, 129-141, 2005; O'Doherty, J. P. Reward representations and reward-related learning in the human brain: Insights from neuroimaging. Current Opinion in Neurobiology, 14, 769-776, 2004; Holroyd, C. B., & Coles, M. G. H. The neural basis of human error processing: Reinforcement learning, dopamine, and the error-related negativity. Psychological Review, 109, 679-709, 2002]. Here, we used the brain ERP technique to demonstrate that not only do rewards elicit a neural response akin to a prediction error but also that this signal rapidly diminished and propagated to the time of choice presentation with learning. Specifically, in a simple, learnable gambling task, we show that novel rewards elicited a feedback error-related negativity that rapidly decreased in amplitude with learning. Furthermore, we demonstrate the existence of a reward positivity at choice presentation, a previously unreported ERP component that has a similar timing and topography as the feedback error-related negativity that increased in amplitude with learning. The pattern of results we observed mirrored the output of a computational model that we implemented to compute reward prediction errors and the changes in amplitude of these prediction errors at the time of choice presentation and reward delivery. Our results provide further support that the computations that underlie human learning and decision-making follow reinforcement learning principles.

Microstimulation of the human substantia nigra alters reinforcement learning.

PubMed

Ramayya, Ashwin G; Misra, Amrit; Baltuch, Gordon H; Kahana, Michael J

2014-05-14

Animal studies have shown that substantia nigra (SN) dopaminergic (DA) neurons strengthen action-reward associations during reinforcement learning, but their role in human learning is not known. Here, we applied microstimulation in the SN of 11 patients undergoing deep brain stimulation surgery for the treatment of Parkinson's disease as they performed a two-alternative probability learning task in which rewards were contingent on stimuli, rather than actions. Subjects demonstrated decreased learning from reward trials that were accompanied by phasic SN microstimulation compared with reward trials without stimulation. Subjects who showed large decreases in learning also showed an increased bias toward repeating actions after stimulation trials; therefore, stimulation may have decreased learning by strengthening action-reward associations rather than stimulus-reward associations. Our findings build on previous studies implicating SN DA neurons in preferentially strengthening action-reward associations during reinforcement learning. Copyright © 2014 the authors 0270-6474/14/346887-09$15.00/0.

Batch Mode Reinforcement Learning based on the Synthesis of Artificial Trajectories

PubMed Central

Fonteneau, Raphael; Murphy, Susan A.; Wehenkel, Louis; Ernst, Damien

2013-01-01

In this paper, we consider the batch mode reinforcement learning setting, where the central problem is to learn from a sample of trajectories a policy that satisfies or optimizes a performance criterion. We focus on the continuous state space case for which usual resolution schemes rely on function approximators either to represent the underlying control problem or to represent its value function. As an alternative to the use of function approximators, we rely on the synthesis of “artificial trajectories” from the given sample of trajectories, and show that this idea opens new avenues for designing and analyzing algorithms for batch mode reinforcement learning. PMID:24049244

Human reinforcement learning subdivides structured action spaces by learning effector-specific values

PubMed Central

Gershman, Samuel J.; Pesaran, Bijan; Daw, Nathaniel D.

2009-01-01

Humans and animals are endowed with a large number of effectors. Although this enables great behavioral flexibility, it presents an equally formidable reinforcement learning problem of discovering which actions are most valuable, due to the high dimensionality of the action space. An unresolved question is how neural systems for reinforcement learning – such as prediction error signals for action valuation associated with dopamine and the striatum – can cope with this “curse of dimensionality.” We propose a reinforcement learning framework that allows for learned action valuations to be decomposed into effector-specific components when appropriate to a task, and test it by studying to what extent human behavior and BOLD activity can exploit such a decomposition in a multieffector choice task. Subjects made simultaneous decisions with their left and right hands and received separate reward feedback for each hand movement. We found that choice behavior was better described by a learning model that decomposed the values of bimanual movements into separate values for each effector, rather than a traditional model that treated the bimanual actions as unitary with a single value. A decomposition of value into effector-specific components was also observed in value-related BOLD signaling, in the form of lateralized biases in striatal correlates of prediction error and anticipatory value correlates in the intraparietal sulcus. These results suggest that the human brain can use decomposed value representations to “divide and conquer” reinforcement learning over high-dimensional action spaces. PMID:19864565

Human reinforcement learning subdivides structured action spaces by learning effector-specific values.

PubMed

Gershman, Samuel J; Pesaran, Bijan; Daw, Nathaniel D

2009-10-28

Humans and animals are endowed with a large number of effectors. Although this enables great behavioral flexibility, it presents an equally formidable reinforcement learning problem of discovering which actions are most valuable because of the high dimensionality of the action space. An unresolved question is how neural systems for reinforcement learning-such as prediction error signals for action valuation associated with dopamine and the striatum-can cope with this "curse of dimensionality." We propose a reinforcement learning framework that allows for learned action valuations to be decomposed into effector-specific components when appropriate to a task, and test it by studying to what extent human behavior and blood oxygen level-dependent (BOLD) activity can exploit such a decomposition in a multieffector choice task. Subjects made simultaneous decisions with their left and right hands and received separate reward feedback for each hand movement. We found that choice behavior was better described by a learning model that decomposed the values of bimanual movements into separate values for each effector, rather than a traditional model that treated the bimanual actions as unitary with a single value. A decomposition of value into effector-specific components was also observed in value-related BOLD signaling, in the form of lateralized biases in striatal correlates of prediction error and anticipatory value correlates in the intraparietal sulcus. These results suggest that the human brain can use decomposed value representations to "divide and conquer" reinforcement learning over high-dimensional action spaces.

The etiology of social change.

PubMed

Carley, Kathleen M; Martin, Michael K; Hirshman, Brian R

2009-10-01

A fundamental aspect of human beings is that they learn. The process of learning and what is learned are impacted by a number of factors, both cognitive and social; that is, humans are boundedly rational. Cognitive and social limitations interact, making it difficult to reason about how to provide information to impact what humans know, believe, and do. Herein, we use a multi-agent dynamic-network simulation system, Construct, to conduct such reasoning. In particular, we ask, What media should be used to provide information to most impact what people know, believe, and do, given diverse social structures? All simulated agents are boundedly rational both at the cognitive and social level, and so are subject to factors such as literacy, education, and the breadth of their social network. We find that there is no one most effective intervention; rather, to be effective, messages and the media used to spread the message need to be selected for the population being addressed. Typically, a multimedia campaign is critical. Copyright © 2009 Cognitive Science Society, Inc.

Learning dynamics in social dilemmas

PubMed Central

Macy, Michael W.; Flache, Andreas

2002-01-01

The Nash equilibrium, the main solution concept in analytical game theory, cannot make precise predictions about the outcome of repeated mixed-motive games. Nor can it tell us much about the dynamics by which a population of players moves from one equilibrium to another. These limitations, along with concerns about the cognitive demands of forward-looking rationality, have motivated efforts to explore backward-looking alternatives to analytical game theory. Most of the effort has been invested in evolutionary models of population dynamics. We shift attention to a learning-theoretic alternative. Computational experiments with adaptive agents identify a fundamental solution concept for social dilemmas–−stochastic collusion–−based on a random walk from a self-limiting noncooperative equilibrium into a self-reinforcing cooperative equilibrium. However, we show that this solution is viable only within a narrow range of aspiration levels. Below the lower threshold, agents are pulled into a deficient equilibrium that is a stronger attractor than mutual cooperation. Above the upper threshold, agents are dissatisfied with mutual cooperation. Aspirations that adapt with experience (producing habituation to stimuli) do not gravitate into the window of viability; rather, they are the worst of both worlds. Habituation destabilizes cooperation and stabilizes defection. Results from the two-person problem suggest that applications to multiplex and embedded relationships will yield unexpected insights into the global dynamics of cooperation in social dilemmas. PMID:12011402

Gossip-based solutions for discrete rendezvous in populations of communicating agents.

PubMed

Hollander, Christopher D; Wu, Annie S

2014-01-01

The objective of the rendezvous problem is to construct a method that enables a population of agents to agree on a spatial (and possibly temporal) meeting location. We introduce the buffered gossip algorithm as a general solution to the rendezvous problem in a discrete domain with direct communication between decentralized agents. We compare the performance of the buffered gossip algorithm against the well known uniform gossip algorithm. We believe that a buffered solution is preferable to an unbuffered solution, such as the uniform gossip algorithm, because the use of a buffer allows an agent to use multiple information sources when determining its desired rendezvous point, and that access to multiple information sources may improve agent decision making by reinforcing or contradicting an initial choice. To show that the buffered gossip algorithm is an actual solution for the rendezvous problem, we construct a theoretical proof of convergence and derive the conditions under which the buffered gossip algorithm is guaranteed to produce a consensus on rendezvous location. We use these results to verify that the uniform gossip algorithm also solves the rendezvous problem. We then use a multi-agent simulation to conduct a series of simulation experiments to compare the performance between the buffered and uniform gossip algorithms. Our results suggest that the buffered gossip algorithm can solve the rendezvous problem faster than the uniform gossip algorithm; however, the relative performance between these two solutions depends on the specific constraints of the problem and the parameters of the buffered gossip algorithm.

Gossip-Based Solutions for Discrete Rendezvous in Populations of Communicating Agents

PubMed Central

Hollander, Christopher D.; Wu, Annie S.

2014-01-01

The objective of the rendezvous problem is to construct a method that enables a population of agents to agree on a spatial (and possibly temporal) meeting location. We introduce the buffered gossip algorithm as a general solution to the rendezvous problem in a discrete domain with direct communication between decentralized agents. We compare the performance of the buffered gossip algorithm against the well known uniform gossip algorithm. We believe that a buffered solution is preferable to an unbuffered solution, such as the uniform gossip algorithm, because the use of a buffer allows an agent to use multiple information sources when determining its desired rendezvous point, and that access to multiple information sources may improve agent decision making by reinforcing or contradicting an initial choice. To show that the buffered gossip algorithm is an actual solution for the rendezvous problem, we construct a theoretical proof of convergence and derive the conditions under which the buffered gossip algorithm is guaranteed to produce a consensus on rendezvous location. We use these results to verify that the uniform gossip algorithm also solves the rendezvous problem. We then use a multi-agent simulation to conduct a series of simulation experiments to compare the performance between the buffered and uniform gossip algorithms. Our results suggest that the buffered gossip algorithm can solve the rendezvous problem faster than the uniform gossip algorithm; however, the relative performance between these two solutions depends on the specific constraints of the problem and the parameters of the buffered gossip algorithm. PMID:25397882

[Effect of amount of silane coupling agent on flexural strength of dental composite resins reinforced with aluminium borate whisker].

PubMed

Zhu, Ming-yi; Zhang, Xiu-yin

2015-06-01

To evaluate the effect of amount of silane coupling agent on flexural strength of dental composite resins reinforced with aluminium borate whisker (ABW). ABW was surface-treated with 0%, 1%, 2%, 3% and 4% silan coupling agent (γ-MPS), and mixed with resin matrix to synthesize 5 groups of composite resins. After heat-cured at 120 degrees centigrade for 1 h, specimens were tested in three-point flexure to measure strength according to ISO-4049. One specimen was selected randomly from each group and observed under scanning electron microscope (SEM). The data was analyzed with SAS 9.2 software package. The flexural strength (117.93±11.9 Mpa) of the group treated with 2% silane coupling agent was the highest, and significantly different from that of the other 4 groups (α=0.01). The amount of silane coupling agent has impact on the flexural strength of dental composite resins reinforced with whiskers; The flexual strength will be reduced whenever the amount is higher or lower than the threshold. Supported by Research Fund of Science and Technology Committee of Shanghai Municipality (08DZ2271100).

Separation of time-based and trial-based accounts of the partial reinforcement extinction effect.

PubMed

Bouton, Mark E; Woods, Amanda M; Todd, Travis P

2014-01-01

Two appetitive conditioning experiments with rats examined time-based and trial-based accounts of the partial reinforcement extinction effect (PREE). In the PREE, the loss of responding that occurs in extinction is slower when the conditioned stimulus (CS) has been paired with a reinforcer on some of its presentations (partially reinforced) instead of every presentation (continuously reinforced). According to a time-based or "time-accumulation" view (e.g., Gallistel and Gibbon, 2000), the PREE occurs because the organism has learned in partial reinforcement to expect the reinforcer after a larger amount of time has accumulated in the CS over trials. In contrast, according to a trial-based view (e.g., Capaldi, 1967), the PREE occurs because the organism has learned in partial reinforcement to expect the reinforcer after a larger number of CS presentations. Experiment 1 used a procedure that equated partially and continuously reinforced groups on their expected times to reinforcement during conditioning. A PREE was still observed. Experiment 2 then used an extinction procedure that allowed time in the CS and the number of trials to accumulate differentially through extinction. The PREE was still evident when responding was examined as a function of expected time units to the reinforcer, but was eliminated when responding was examined as a function of expected trial units to the reinforcer. There was no evidence that the animal responded according to the ratio of time accumulated during the CS in extinction over the time in the CS expected before the reinforcer. The results thus favor a trial-based account over a time-based account of extinction and the PREE. This article is part of a Special Issue entitled: Associative and Temporal Learning. Copyright © 2013 Elsevier B.V. All rights reserved.

Autonomous reinforcement learning with experience replay.

PubMed

Wawrzyński, Paweł; Tanwani, Ajay Kumar

2013-05-01

This paper considers the issues of efficiency and autonomy that are required to make reinforcement learning suitable for real-life control tasks. A real-time reinforcement learning algorithm is presented that repeatedly adjusts the control policy with the use of previously collected samples, and autonomously estimates the appropriate step-sizes for the learning updates. The algorithm is based on the actor-critic with experience replay whose step-sizes are determined on-line by an enhanced fixed point algorithm for on-line neural network training. An experimental study with simulated octopus arm and half-cheetah demonstrates the feasibility of the proposed algorithm to solve difficult learning control problems in an autonomous way within reasonably short time. Copyright © 2012 Elsevier Ltd. All rights reserved.

Electrophysiological correlates of reinforcement learning in young people with Tourette syndrome with and without co-occurring ADHD symptoms.

PubMed

Shephard, Elizabeth; Jackson, Georgina M; Groom, Madeleine J

2016-06-01

Altered reinforcement learning is implicated in the causes of Tourette syndrome (TS) and attention-deficit/hyperactivity disorder (ADHD). TS and ADHD frequently co-occur but how this affects reinforcement learning has not been investigated. We examined the ability of young people with TS (n=18), TS+ADHD (N=17), ADHD (n=13) and typically developing controls (n=20) to learn and reverse stimulus-response (S-R) associations based on positive and negative reinforcement feedback. We used a 2 (TS-yes, TS-no)×2 (ADHD-yes, ADHD-no) factorial design to assess the effects of TS, ADHD, and their interaction on behavioural (accuracy, RT) and event-related potential (stimulus-locked P3, feedback-locked P2, feedback-related negativity, FRN) indices of learning and reversing the S-R associations. TS was associated with intact learning and reversal performance and largely typical ERP amplitudes. ADHD was associated with lower accuracy during S-R learning and impaired reversal learning (significantly reduced accuracy and a trend for smaller P3 amplitude). The results indicate that co-occurring ADHD symptoms impair reversal learning in TS+ADHD. The implications of these findings for behavioural tic therapies are discussed. Copyright © 2016 ISDN. Published by Elsevier Ltd. All rights reserved.

Utilising reinforcement learning to develop strategies for driving auditory neural implants.

PubMed

Lee, Geoffrey W; Zambetta, Fabio; Li, Xiaodong; Paolini, Antonio G

2016-08-01

In this paper we propose a novel application of reinforcement learning to the area of auditory neural stimulation. We aim to develop a simulation environment which is based off real neurological responses to auditory and electrical stimulation in the cochlear nucleus (CN) and inferior colliculus (IC) of an animal model. Using this simulator we implement closed loop reinforcement learning algorithms to determine which methods are most effective at learning effective acoustic neural stimulation strategies. By recording a comprehensive set of acoustic frequency presentations and neural responses from a set of animals we created a large database of neural responses to acoustic stimulation. Extensive electrical stimulation in the CN and the recording of neural responses in the IC provides a mapping of how the auditory system responds to electrical stimuli. The combined dataset is used as the foundation for the simulator, which is used to implement and test learning algorithms. Reinforcement learning, utilising a modified n-Armed Bandit solution, is implemented to demonstrate the model's function. We show the ability to effectively learn stimulation patterns which mimic the cochlea's ability to covert acoustic frequencies to neural activity. Time taken to learn effective replication using neural stimulation takes less than 20 min under continuous testing. These results show the utility of reinforcement learning in the field of neural stimulation. These results can be coupled with existing sound processing technologies to develop new auditory prosthetics that are adaptable to the recipients current auditory pathway. The same process can theoretically be abstracted to other sensory and motor systems to develop similar electrical replication of neural signals.

Embedded Incremental Feature Selection for Reinforcement Learning

DTIC Science & Technology

2012-05-01

Prior to this work, feature selection for reinforce- ment learning has focused on linear value function ap- proximation ( Kolter and Ng, 2009; Parr et al...InProceed- ings of the the 23rd International Conference on Ma- chine Learning, pages 449–456. Kolter , J. Z. and Ng, A. Y. (2009). Regularization and feature

Social Learning, Reinforcement and Crime: Evidence from Three European Cities

ERIC Educational Resources Information Center

Tittle, Charles R.; Antonaccio, Olena; Botchkovar, Ekaterina

2012-01-01

This study reports a cross-cultural test of Social Learning Theory using direct measures of social learning constructs and focusing on the causal structure implied by the theory. Overall, the results strongly confirm the main thrust of the theory. Prior criminal reinforcement and current crime-favorable definitions are highly related in all three…

Novelty and Inductive Generalization in Human Reinforcement Learning

PubMed Central

Gershman, Samuel J.; Niv, Yael

2015-01-01

In reinforcement learning, a decision maker searching for the most rewarding option is often faced with the question: what is the value of an option that has never been tried before? One way to frame this question is as an inductive problem: how can I generalize my previous experience with one set of options to a novel option? We show how hierarchical Bayesian inference can be used to solve this problem, and describe an equivalence between the Bayesian model and temporal difference learning algorithms that have been proposed as models of reinforcement learning in humans and animals. According to our view, the search for the best option is guided by abstract knowledge about the relationships between different options in an environment, resulting in greater search efficiency compared to traditional reinforcement learning algorithms previously applied to human cognition. In two behavioral experiments, we test several predictions of our model, providing evidence that humans learn and exploit structured inductive knowledge to make predictions about novel options. In light of this model, we suggest a new interpretation of dopaminergic responses to novelty. PMID:25808176

Learning with incomplete information and the mathematical structure behind it.

PubMed

Kühn, Reimer; Stamatescu, Ion-Olimpiu

2007-07-01

We investigate the problem of learning with incomplete information as exemplified by learning with delayed reinforcement. We study a two phase learning scenario in which a phase of Hebbian associative learning based on momentary internal representations is supplemented by an 'unlearning' phase depending on a graded reinforcement signal. The reinforcement signal quantifies the success-rate globally for a number of learning steps in phase one, and 'unlearning' is indiscriminate with respect to associations learnt in that phase. Learning according to this model is studied via simulations and analytically within a student-teacher scenario for both single layer networks and, for a committee machine. Success and speed of learning depend on the ratio lambda of the learning rates used for the associative Hebbian learning phase and for the unlearning-correction in response to the reinforcement signal, respectively. Asymptotically perfect generalization is possible only, if this ratio exceeds a critical value lambda( c ), in which case the generalization error exhibits a power law decay with the number of examples seen by the student, with an exponent that depends in a non-universal manner on the parameter lambda. We find these features to be robust against a wide spectrum of modifications of microscopic modelling details. Two illustrative applications-one of a robot learning to navigate a field containing obstacles, and the problem of identifying a specific component in a collection of stimuli-are also provided.

Framing Reinforcement Learning from Human Reward: Reward Positivity, Temporal Discounting, Episodicity, and Performance

DTIC Science & Technology

2014-09-29

Framing Reinforcement Learning from Human Reward: Reward Positivity, Temporal Discounting, Episodicity , and Performance W. Bradley Knox...positive a trainer’s reward values are; temporal discounting, the extent to which future reward is discounted in value; episodicity , whether task...learning occurs in discrete learning episodes instead of one continuing session; and task performance, the agent’s performance on the task the trainer

Multi-Length Scale-Enriched Continuum-Level Material Model for Kevlar (registered trademark)-Fiber-Reinforced Polymer-Matrix Composites

DTIC Science & Technology

2013-03-01

of coarser-scale materials and structures containing Kevlar fibers (e.g., yarns, fabrics, plies, lamina, and laminates ). Journal of Materials...Multi-Length Scale-Enriched Continuum-Level Material Model for Kevlar -Fiber-Reinforced Polymer-Matrix Composites M. Grujicic, B. Pandurangan, J.S...extensive set of molecular-level computational analyses regarding the role of various microstructural/morphological defects on the Kevlar fiber

Nanoparticles for cancer imaging: The good, the bad, and the promise

PubMed Central

Chapman, Sandra; Dobrovolskaia, Marina; Farahani, Keyvan; Goodwin, Andrew; Joshi, Amit; Lee, Hakho; Meade, Thomas; Pomper, Martin; Ptak, Krzysztof; Rao, Jianghong; Singh, Ravi; Sridhar, Srinivas; Stern, Stephan; Wang, Andrew; Weaver, John B.; Woloschak, Gayle; Yang, Lily

2014-01-01

Summary Recent advances in molecular imaging and nanotechnology are providing new opportunities for biomedical imaging with great promise for the development of novel imaging agents. The unique optical, magnetic, and chemical properties of materials at the scale of nanometers allow the creation of imaging probes with better contrast enhancement, increased sensitivity, controlled biodistribution, better spatial and temporal information, multi-functionality and multi-modal imaging across MRI, PET, SPECT, and ultrasound. These features could ultimately translate to clinical advantages such as earlier detection, real time assessment of disease progression and personalized medicine. However, several years of investigation into the application of these materials to cancer research has revealed challenges that have delayed the successful application of these agents to the field of biomedical imaging. Understanding these challenges is critical to take full advantage of the benefits offered by nano-sized imaging agents. Therefore, this article presents the lessons learned and challenges encountered by a group of leading researchers in this field, and suggests ways forward to develop nanoparticle probes for cancer imaging. Published by Elsevier Ltd. PMID:25419228

Exploration of Force Transition in Stability Operations Using Multi-Agent Simulation

DTIC Science & Technology

2006-09-01

risk, mission failure risk, and time in the context of the operational threat environment. The Pythagoras Multi-Agent Simulation and Data Farming...NUMBER OF PAGES 173 14. SUBJECT TERMS Stability Operations, Peace Operations, Data Farming, Pythagoras , Agent- Based Model, Multi-Agent Simulation...the operational threat environment. The Pythagoras Multi-Agent Simulation and Data Farming techniques are used to investigate force-level

The effect of music reinforcement for non-nutritive sucking on nipple feeding of premature infants.

PubMed

Standley, Jayne M; Cassidy, Jane; Grant, Roy; Cevasco, Andrea; Szuch, Catherine; Nguyen, Judy; Walworth, Darcy; Procelli, Danielle; Jarred, Jennifer; Adams, Kristen

2010-01-01

In this randomized, controlled multi-site study, the pacifier-activated-lullaby system (PAL) was used with 68 premature infants. Dependent variables were (a) total number of days prior to nipple feeding, (b) days of nipple feeding, (c) discharge weight, and (d) overall weight gain. Independent variables included contingent music reinforcement for non-nutritive sucking for PAL intervention at 32 vs. 34 vs. 36 weeks adjusted gestational age (AGA), with each age group subdivided into three trial conditions: control consisting of no PAL used vs. one 15-minute PAL trial vs. three 15-minute PAL trials. At 34 weeks, PAL trials significantly shortened gavage feeding length, and three trials were significantly better than one trial. At 32 weeks, PAL trials lengthened gavage feeding. Female infants learned to nipple feed significantly faster than male infants. It was noted that PAL babies went home sooner after beginning to nipple feed, a trend that was not statistically significant.

Framework for robot skill learning using reinforcement learning

NASA Astrophysics Data System (ADS)

Wei, Yingzi; Zhao, Mingyang

2003-09-01

Robot acquiring skill is a process similar to human skill learning. Reinforcement learning (RL) is an on-line actor critic method for a robot to develop its skill. The reinforcement function has become the critical component for its effect of evaluating the action and guiding the learning process. We present an augmented reward function that provides a new way for RL controller to incorporate prior knowledge and experience into the RL controller. Also, the difference form of augmented reward function is considered carefully. The additional reward beyond conventional reward will provide more heuristic information for RL. In this paper, we present a strategy for the task of complex skill learning. Automatic robot shaping policy is to dissolve the complex skill into a hierarchical learning process. The new form of value function is introduced to attain smooth motion switching swiftly. We present a formal, but practical, framework for robot skill learning and also illustrate with an example the utility of method for learning skilled robot control on line.

Multi-Observation Continuous Density Hidden Markov Models for Anomaly Detection in Full Motion Video

DTIC Science & Technology

2012-06-01

response profiles . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47 3.5 Method for measuring angular movement versus average direction...of movement 49 3.6 Method for calculating Angular Deviation, Θ . . . . . . . . . . . . . . . . . . 50 4.1 HMM produced by K Means Learning for agent H... Angular Deviation. A random variable, the difference in heading (in degrees) from the overall direction of movement over the sequence • S : Speed. A

Workshop on Planning and Learning in Multi- Agent Environments

DTIC Science & Technology

2014-12-31

needed for translating the physical aspects of an interaction (see Section 3.1) into the numeric utility values needed for game -theoretic...calculations. Furthermore, the game -theoretic techniques themselves will require significant enhancements. Game -theoretic solution concepts (e.g., Nash...robotics. Real-time strategy games may provide useful data for research on predictive models of ad- versaries, modeling long-term and short-term plans

Proactivity and Reinforcement: The Contingency of Social Behavior

ERIC Educational Resources Information Center

Williams, J. Sherwood; And Others

1976-01-01

This paper analyzes development of group structure in terms of the stimulus-sampling perspective. Learning is the continual sampling of possibilities, with those reinforced possibilities increasing in probability of occurance. This contingency learning approach is tested experimentally. (NG)

Mobile robots exploration through cnn-based reinforcement learning.

PubMed

Tai, Lei; Liu, Ming

2016-01-01

Exploration in an unknown environment is an elemental application for mobile robots. In this paper, we outlined a reinforcement learning method aiming for solving the exploration problem in a corridor environment. The learning model took the depth image from an RGB-D sensor as the only input. The feature representation of the depth image was extracted through a pre-trained convolutional-neural-networks model. Based on the recent success of deep Q-network on artificial intelligence, the robot controller achieved the exploration and obstacle avoidance abilities in several different simulated environments. It is the first time that the reinforcement learning is used to build an exploration strategy for mobile robots through raw sensor information.

Altered neural encoding of prediction errors in assault-related posttraumatic stress disorder.

PubMed

Ross, Marisa C; Lenow, Jennifer K; Kilts, Clinton D; Cisler, Josh M

2018-05-12

Posttraumatic stress disorder (PTSD) is widely associated with deficits in extinguishing learned fear responses, which relies on mechanisms of reinforcement learning (e.g., updating expectations based on prediction errors). However, the degree to which PTSD is associated with impairments in general reinforcement learning (i.e., outside of the context of fear stimuli) remains poorly understood. Here, we investigate brain and behavioral differences in general reinforcement learning between adult women with and without a current diagnosis of PTSD. 29 adult females (15 PTSD with exposure to assaultive violence, 14 controls) underwent a neutral reinforcement-learning task (i.e., two arm bandit task) during fMRI. We modeled participant behavior using different adaptations of the Rescorla-Wagner (RW) model and used Independent Component Analysis to identify timecourses for large-scale a priori brain networks. We found that an anticorrelated and risk sensitive RW model best fit participant behavior, with no differences in computational parameters between groups. Women in the PTSD group demonstrated significantly less neural encoding of prediction errors in both a ventral striatum/mPFC and anterior insula network compared to healthy controls. Weakened encoding of prediction errors in the ventral striatum/mPFC and anterior insula during a general reinforcement learning task, outside of the context of fear stimuli, suggests the possibility of a broader conceptualization of learning differences in PTSD than currently proposed in current neurocircuitry models of PTSD. Copyright © 2018 Elsevier Ltd. All rights reserved.

Automated Inattention and Fatigue Detection System in Distance Education for Elementary School Students

ERIC Educational Resources Information Center

Hwang, Kuo-An; Yang, Chia-Hao

2009-01-01

Most courses based on distance learning focus on the cognitive domain of learning. Because students are sometimes inattentive or tired, they may neglect the attention goal of learning. This study proposes an auto-detection and reinforcement mechanism for the distance-education system based on the reinforcement teaching strategy. If a student is…

When, What, and How Much to Reward in Reinforcement Learning-Based Models of Cognition

ERIC Educational Resources Information Center

Janssen, Christian P.; Gray, Wayne D.

2012-01-01

Reinforcement learning approaches to cognitive modeling represent task acquisition as learning to choose the sequence of steps that accomplishes the task while maximizing a reward. However, an apparently unrecognized problem for modelers is choosing when, what, and how much to reward; that is, when (the moment: end of trial, subtask, or some other…

Dissociating error-based and reinforcement-based loss functions during sensorimotor learning

PubMed Central

McGregor, Heather R.; Mohatarem, Ayman

2017-01-01

It has been proposed that the sensorimotor system uses a loss (cost) function to evaluate potential movements in the presence of random noise. Here we test this idea in the context of both error-based and reinforcement-based learning. In a reaching task, we laterally shifted a cursor relative to true hand position using a skewed probability distribution. This skewed probability distribution had its mean and mode separated, allowing us to dissociate the optimal predictions of an error-based loss function (corresponding to the mean of the lateral shifts) and a reinforcement-based loss function (corresponding to the mode). We then examined how the sensorimotor system uses error feedback and reinforcement feedback, in isolation and combination, when deciding where to aim the hand during a reach. We found that participants compensated differently to the same skewed lateral shift distribution depending on the form of feedback they received. When provided with error feedback, participants compensated based on the mean of the skewed noise. When provided with reinforcement feedback, participants compensated based on the mode. Participants receiving both error and reinforcement feedback continued to compensate based on the mean while repeatedly missing the target, despite receiving auditory, visual and monetary reinforcement feedback that rewarded hitting the target. Our work shows that reinforcement-based and error-based learning are separable and can occur independently. Further, when error and reinforcement feedback are in conflict, the sensorimotor system heavily weights error feedback over reinforcement feedback. PMID:28753634

Dissociating error-based and reinforcement-based loss functions during sensorimotor learning.

PubMed

Cashaback, Joshua G A; McGregor, Heather R; Mohatarem, Ayman; Gribble, Paul L

2017-07-01

It has been proposed that the sensorimotor system uses a loss (cost) function to evaluate potential movements in the presence of random noise. Here we test this idea in the context of both error-based and reinforcement-based learning. In a reaching task, we laterally shifted a cursor relative to true hand position using a skewed probability distribution. This skewed probability distribution had its mean and mode separated, allowing us to dissociate the optimal predictions of an error-based loss function (corresponding to the mean of the lateral shifts) and a reinforcement-based loss function (corresponding to the mode). We then examined how the sensorimotor system uses error feedback and reinforcement feedback, in isolation and combination, when deciding where to aim the hand during a reach. We found that participants compensated differently to the same skewed lateral shift distribution depending on the form of feedback they received. When provided with error feedback, participants compensated based on the mean of the skewed noise. When provided with reinforcement feedback, participants compensated based on the mode. Participants receiving both error and reinforcement feedback continued to compensate based on the mean while repeatedly missing the target, despite receiving auditory, visual and monetary reinforcement feedback that rewarded hitting the target. Our work shows that reinforcement-based and error-based learning are separable and can occur independently. Further, when error and reinforcement feedback are in conflict, the sensorimotor system heavily weights error feedback over reinforcement feedback.

Altered Risk-Based Decision Making following Adolescent Alcohol Use Results from an Imbalance in Reinforcement Learning in Rats

PubMed Central

Hart, Andrew S.; Collins, Anne L.; Bernstein, Ilene L.; Phillips, Paul E. M.

2012-01-01

Alcohol use during adolescence has profound and enduring consequences on decision-making under risk. However, the fundamental psychological processes underlying these changes are unknown. Here, we show that alcohol use produces over-fast learning for better-than-expected, but not worse-than-expected, outcomes without altering subjective reward valuation. We constructed a simple reinforcement learning model to simulate altered decision making using behavioral parameters extracted from rats with a history of adolescent alcohol use. Remarkably, the learning imbalance alone was sufficient to simulate the divergence in choice behavior observed between these groups of animals. These findings identify a selective alteration in reinforcement learning following adolescent alcohol use that can account for a robust change in risk-based decision making persisting into later life. PMID:22615989

A Distributed Ambient Intelligence Based Multi-Agent System for Alzheimer Health Care

NASA Astrophysics Data System (ADS)

Tapia, Dante I.; RodríGuez, Sara; Corchado, Juan M.

This chapter presents ALZ-MAS (Alzheimer multi-agent system), an ambient intelligence (AmI)-based multi-agent system aimed at enhancing the assistance and health care for Alzheimer patients. The system makes use of several context-aware technologies that allow it to automatically obtain information from users and the environment in an evenly distributed way, focusing on the characteristics of ubiquity, awareness, intelligence, mobility, etc., all of which are concepts defined by AmI. ALZ-MAS makes use of a services oriented multi-agent architecture, called flexible user and services oriented multi-agent architecture, to distribute resources and enhance its performance. It is demonstrated that a SOA approach is adequate to build distributed and highly dynamic AmI-based multi-agent systems.

A Discussion of Possibility of Reinforcement Learning Using Event-Related Potential in BCI

NASA Astrophysics Data System (ADS)

Yamagishi, Yuya; Tsubone, Tadashi; Wada, Yasuhiro

Recently, Brain computer interface (BCI) which is a direct connecting pathway an external device such as a computer or a robot and a human brain have gotten a lot of attention. Since BCI can control the machines as robots by using the brain activity without using the voluntary muscle, the BCI may become a useful communication tool for handicapped persons, for instance, amyotrophic lateral sclerosis patients. However, in order to realize the BCI system which can perform precise tasks on various environments, it is necessary to design the control rules to adapt to the dynamic environments. Reinforcement learning is one approach of the design of the control rule. If this reinforcement leaning can be performed by the brain activity, it leads to the attainment of BCI that has general versatility. In this research, we paid attention to P300 of event-related potential as an alternative signal of the reward of reinforcement learning. We discriminated between the success and the failure trials from P300 of the EEG of the single trial by using the proposed discrimination algorithm based on Support vector machine. The possibility of reinforcement learning was examined from the viewpoint of the number of discriminated trials. It was shown that there was a possibility to be able to learn in most subjects.

Comparative learning theory and its application in the training of horses.

PubMed

Cooper, J J

1998-11-01

Training can best be explained as a process that occurs through stimulus-response-reinforcement chains, whereby animals are conditioned to associate cues in their environment, with specific behavioural responses and their rewarding consequences. Research into learning in horses has concentrated on their powers of discrimination and on primary positive reinforcement schedules, where the correct response is paired with a desirable consequence such as food. In contrast, a number of other learning processes that are used in training have been widely studied in other species, but have received little scientific investigation in the horse. These include: negative reinforcement, where performance of the correct response is followed by removal of, or decrease in, intensity of a unpleasant stimulus; punishment, where an incorrect response is paired with an undesirable consequence, but without consistent prior warning; secondary conditioning, where a natural primary reinforcer such as food is closely associated with an arbitrary secondary reinforcer such as vocal praise; and variable or partial conditioning, where once the correct response has been learnt, reinforcement is presented according to an intermittent schedule to increase resistance to extinction outside of training.

Predicting Pilot Behavior in Medium Scale Scenarios Using Game Theory and Reinforcement Learning

NASA Technical Reports Server (NTRS)

Yildiz, Yildiray; Agogino, Adrian; Brat, Guillaume

2013-01-01

Effective automation is critical in achieving the capacity and safety goals of the Next Generation Air Traffic System. Unfortunately creating integration and validation tools for such automation is difficult as the interactions between automation and their human counterparts is complex and unpredictable. This validation becomes even more difficult as we integrate wide-reaching technologies that affect the behavior of different decision makers in the system such as pilots, controllers and airlines. While overt short-term behavior changes can be explicitly modeled with traditional agent modeling systems, subtle behavior changes caused by the integration of new technologies may snowball into larger problems and be very hard to detect. To overcome these obstacles, we show how integration of new technologies can be validated by learning behavior models based on goals. In this framework, human participants are not modeled explicitly. Instead, their goals are modeled and through reinforcement learning their actions are predicted. The main advantage to this approach is that modeling is done within the context of the entire system allowing for accurate modeling of all participants as they interact as a whole. In addition such an approach allows for efficient trade studies and feasibility testing on a wide range of automation scenarios. The goal of this paper is to test that such an approach is feasible. To do this we implement this approach using a simple discrete-state learning system on a scenario where 50 aircraft need to self-navigate using Automatic Dependent Surveillance-Broadcast (ADS-B) information. In this scenario, we show how the approach can be used to predict the ability of pilots to adequately balance aircraft separation and fly efficient paths. We present results with several levels of complexity and airspace congestion.

The nature of sexual reinforcement.

PubMed Central

Crawford, L L; Holloway, K S; Domjan, M

1993-01-01

Sexual reinforcers are not part of a regulatory system involved in the maintenance of critical metabolic processes, they differ for males and females, they differ as a function of species and mating system, and they show ontogenetic and seasonal changes related to endocrine conditions. Exposure to a member of the opposite sex without copulation can be sufficient for sexual reinforcement. However, copulatory access is a stronger reinforcer, and copulatory opportunity can serve to enhance the reinforcing efficacy of stimulus features of a sexual partner. Conversely, under certain conditions, noncopulatory exposure serves to decrease reinforcer efficacy. Many common learning phenomena such as acquisition, extinction, discrimination learning, second-order conditioning, and latent inhibition have been demonstrated in sexual conditioning. These observations extend the generality of findings obtained with more conventional reinforcers, but the mechanisms of these effects and their gender and species specificity remain to be explored. PMID:8354970

Mesolimbic confidence signals guide perceptual learning in the absence of external feedback

PubMed Central

Guggenmos, Matthias; Wilbertz, Gregor; Hebart, Martin N; Sterzer, Philipp

2016-01-01

It is well established that learning can occur without external feedback, yet normative reinforcement learning theories have difficulties explaining such instances of learning. Here, we propose that human observers are capable of generating their own feedback signals by monitoring internal decision variables. We investigated this hypothesis in a visual perceptual learning task using fMRI and confidence reports as a measure for this monitoring process. Employing a novel computational model in which learning is guided by confidence-based reinforcement signals, we found that mesolimbic brain areas encoded both anticipation and prediction error of confidence—in remarkable similarity to previous findings for external reward-based feedback. We demonstrate that the model accounts for choice and confidence reports and show that the mesolimbic confidence prediction error modulation derived through the model predicts individual learning success. These results provide a mechanistic neurobiological explanation for learning without external feedback by augmenting reinforcement models with confidence-based feedback. DOI: http://dx.doi.org/10.7554/eLife.13388.001 PMID:27021283

Phasic dopamine as a prediction error of intrinsic and extrinsic reinforcements driving both action acquisition and reward maximization: a simulated robotic study.

PubMed

Mirolli, Marco; Santucci, Vieri G; Baldassarre, Gianluca

2013-03-01

An important issue of recent neuroscientific research is to understand the functional role of the phasic release of dopamine in the striatum, and in particular its relation to reinforcement learning. The literature is split between two alternative hypotheses: one considers phasic dopamine as a reward prediction error similar to the computational TD-error, whose function is to guide an animal to maximize future rewards; the other holds that phasic dopamine is a sensory prediction error signal that lets the animal discover and acquire novel actions. In this paper we propose an original hypothesis that integrates these two contrasting positions: according to our view phasic dopamine represents a TD-like reinforcement prediction error learning signal determined by both unexpected changes in the environment (temporary, intrinsic reinforcements) and biological rewards (permanent, extrinsic reinforcements). Accordingly, dopamine plays the functional role of driving both the discovery and acquisition of novel actions and the maximization of future rewards. To validate our hypothesis we perform a series of experiments with a simulated robotic system that has to learn different skills in order to get rewards. We compare different versions of the system in which we vary the composition of the learning signal. The results show that only the system reinforced by both extrinsic and intrinsic reinforcements is able to reach high performance in sufficiently complex conditions. Copyright © 2013 Elsevier Ltd. All rights reserved.

A review of the feasibility of lightening structural polymeric composites with voids without compromising mechanical properties.

PubMed

Rutz, Benjamin H; Berg, John C

2010-10-15

High performance polymer-fiber composites are high strength, low weight materials that have many applications, many of which would benefit from a decrease in weight, without a decrease in material properties. Generally, the fibers serve as the main load carriers, while the matrix serves to distribute load and protect the fibers from the environment. Thus, it is postulated that if the volume fraction of matrix is reduced, while still ensuring complete wetting of the fibers by the matrix, the per unit weight, i.e., specific, mechanical properties could be improved. This can be done by introducing small, spherical bubbles. Given the small average inter-fiber distance and assuming that the bubbles must not interact with the surface of the reinforcements the bubble diameter would need to be less than 1 μm. Introducing bubbles this small and ensuring that they do not form, or become attached, on the surface of the reinforcement are significant challenges. Two methods to produce such bubbles and the effect of these bubbles on mechanical properties of neat resins are reviewed: the addition of hollow spherical fillers, called microballoons, and the creation of bubbles from blowing agents. Microballoons in resins are a class of materials called syntactic foams. Although commercial microballoons are too large, smaller diameters can be made and could be used to reduce the weight of a reinforced composite on the order of 10%. The use of a physical blowing agent to produce bubbles in a composite is also considered. However, traditional polymer foaming techniques may be inadequate, as nucleation on the reinforcing phase is likely, and the bubbles formed are generally too large, so the use of blowing agent wells is considered. Blowing agent wells are discontinuous regions made from copolymer micelles or immiscible polymers that act as reservoirs of blowing agent. Additionally, the use of nano-sized materials for use as heterogeneous nucleation sites and secondary reinforcement of the matrix is also considered. Bubbles made from blowing agent could reduce the weight slightly more than using hollow spheres, but the reduction would also be of the order of 10%. Copyright © 2010 Elsevier B.V. All rights reserved.

Within- and across-trial dynamics of human EEG reveal cooperative interplay between reinforcement learning and working memory.

PubMed

Collins, Anne G E; Frank, Michael J

2018-03-06

Learning from rewards and punishments is essential to survival and facilitates flexible human behavior. It is widely appreciated that multiple cognitive and reinforcement learning systems contribute to decision-making, but the nature of their interactions is elusive. Here, we leverage methods for extracting trial-by-trial indices of reinforcement learning (RL) and working memory (WM) in human electro-encephalography to reveal single-trial computations beyond that afforded by behavior alone. Neural dynamics confirmed that increases in neural expectation were predictive of reduced neural surprise in the following feedback period, supporting central tenets of RL models. Within- and cross-trial dynamics revealed a cooperative interplay between systems for learning, in which WM contributes expectations to guide RL, despite competition between systems during choice. Together, these results provide a deeper understanding of how multiple neural systems interact for learning and decision-making and facilitate analysis of their disruption in clinical populations.

Learning and tuning fuzzy logic controllers through reinforcements.

PubMed

Berenji, H R; Khedkar, P

1992-01-01

A method for learning and tuning a fuzzy logic controller based on reinforcements from a dynamic system is presented. It is shown that: the generalized approximate-reasoning-based intelligent control (GARIC) architecture learns and tunes a fuzzy logic controller even when only weak reinforcement, such as a binary failure signal, is available; introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; introduces a new localized mean of maximum (LMOM) method in combining the conclusions of several firing control rules; and learns to produce real-valued control actions. Learning is achieved by integrating fuzzy inference into a feedforward network, which can then adaptively improve performance by using gradient descent methods. The GARIC architecture is applied to a cart-pole balancing system and demonstrates significant improvements in terms of the speed of learning and robustness to changes in the dynamic system's parameters over previous schemes for cart-pole balancing.

Theoretical and practical aspects of improving the durability of steel reinforcement in transport designs, using passivation and plasticizing chemical additives

NASA Astrophysics Data System (ADS)

Velichko, Evgenij; Talipov, Linar

2017-10-01

The article deals with the problem of steel reinforcement corrosion in reinforced concrete structures exposed to aggressive media, in particular in reinforced concrete construction of transport infrastructure, in snowy areas, and subject to the influence of chlorides contained in applied deicing agents. Basic schemes for preventing the reinforcement corrosion in reinforced-concrete structures have been considered and analyzed. Prospects of primary protection against corrosion of reinforcement by introducing chemical additives with plasticizing/passivating action in a concrete mixture with mixing water have been considered in detail. The physical/chemical mechanism of the protective action of a superplasticizer together with a passivator has been highlighted.

Impairments in action-outcome learning in schizophrenia.

PubMed

Morris, Richard W; Cyrzon, Chad; Green, Melissa J; Le Pelley, Mike E; Balleine, Bernard W

2018-03-03

Learning the causal relation between actions and their outcomes (AO learning) is critical for goal-directed behavior when actions are guided by desire for the outcome. This can be contrasted with habits that are acquired by reinforcement and primed by prevailing stimuli, in which causal learning plays no part. Recently, we demonstrated that goal-directed actions are impaired in schizophrenia; however, whether this deficit exists alongside impairments in habit or reinforcement learning is unknown. The present study distinguished deficits in causal learning from reinforcement learning in schizophrenia. We tested people with schizophrenia (SZ, n = 25) and healthy adults (HA, n = 25) in a vending machine task. Participants learned two action-outcome contingencies (e.g., push left to get a chocolate M&M, push right to get a cracker), and they also learned one contingency was degraded by delivery of noncontingent outcomes (e.g., free M&Ms), as well as changes in value by outcome devaluation. Both groups learned the best action to obtain rewards; however, SZ did not distinguish the more causal action when one AO contingency was degraded. Moreover, action selection in SZ was insensitive to changes in outcome value unless feedback was provided, and this was related to the deficit in AO learning. The failure to encode the causal relation between action and outcome in schizophrenia occurred without any apparent deficit in reinforcement learning. This implies that poor goal-directed behavior in schizophrenia cannot be explained by a more primary deficit in reward learning such as insensitivity to reward value or reward prediction errors.

SpikingLab: modelling agents controlled by Spiking Neural Networks in Netlogo.

PubMed

Jimenez-Romero, Cristian; Johnson, Jeffrey

2017-01-01

The scientific interest attracted by Spiking Neural Networks (SNN) has lead to the development of tools for the simulation and study of neuronal dynamics ranging from phenomenological models to the more sophisticated and biologically accurate Hodgkin-and-Huxley-based and multi-compartmental models. However, despite the multiple features offered by neural modelling tools, their integration with environments for the simulation of robots and agents can be challenging and time consuming. The implementation of artificial neural circuits to control robots generally involves the following tasks: (1) understanding the simulation tools, (2) creating the neural circuit in the neural simulator, (3) linking the simulated neural circuit with the environment of the agent and (4) programming the appropriate interface in the robot or agent to use the neural controller. The accomplishment of the above-mentioned tasks can be challenging, especially for undergraduate students or novice researchers. This paper presents an alternative tool which facilitates the simulation of simple SNN circuits using the multi-agent simulation and the programming environment Netlogo (educational software that simplifies the study and experimentation of complex systems). The engine proposed and implemented in Netlogo for the simulation of a functional model of SNN is a simplification of integrate and fire (I&F) models. The characteristics of the engine (including neuronal dynamics, STDP learning and synaptic delay) are demonstrated through the implementation of an agent representing an artificial insect controlled by a simple neural circuit. The setup of the experiment and its outcomes are described in this work.

The Effects of a Token Reinforcement System on the Reading and Arithmetic Skills Learnings of Migrant Primary School Pupils.

ERIC Educational Resources Information Center

Heitzman, Andrew J.

The New York State Center for Migrant Studies conducted this 1968 study which investigated effects of token reinforcers on reading and arithmetic skills learnings of migrant primary school students during a 6-week summer school session. Students (Negro and Caucasian) received plastic tokens to reward skills learning responses. Tokens were traded…

The Effects of Observation of Learn Units during Reinforcement and Correction Conditions on the Rate of Learning Math Algorithms by Fifth Grade Students

ERIC Educational Resources Information Center

Neu, Jessica Adele

2013-01-01

I conducted two studies on the comparative effects of the observation of learn units during (a) reinforcement or (b) correction conditions on the acquisition of math objectives. The dependent variables were the within-session cumulative numbers of correct responses emitted during observational sessions. The independent variables were the…

An Evaluation of Pedagogical Tutorial Tactics for a Natural Language Tutoring System: A Reinforcement Learning Approach

ERIC Educational Resources Information Center

Chi, Min; VanLehn, Kurt; Litman, Diane; Jordan, Pamela

2011-01-01

Pedagogical strategies are policies for a tutor to decide the next action when there are multiple actions available. When the content is controlled to be the same across experimental conditions, there has been little evidence that tutorial decisions have an impact on students' learning. In this paper, we applied Reinforcement Learning (RL) to…

The Identification and Establishment of Reinforcement for Collaboration in Elementary Students

ERIC Educational Resources Information Center

Darcy, Laura

2017-01-01

In Experiment 1, I conducted a functional analysis of student rate of learning with and without a peer-yoked contingency for 12 students in Kindergarten through 2nd grade in order to determine if they had conditioned reinforcement for collaboration. Using an ABAB reversal design, I compared rate of learning as measured by learn units to criterion…

Stress enhances model-free reinforcement learning only after negative outcome

PubMed Central

Lee, Daeyeol

2017-01-01

Previous studies found that stress shifts behavioral control by promoting habits while decreasing goal-directed behaviors during reward-based decision-making. It is, however, unclear how stress disrupts the relative contribution of the two systems controlling reward-seeking behavior, i.e. model-free (or habit) and model-based (or goal-directed). Here, we investigated whether stress biases the contribution of model-free and model-based reinforcement learning processes differently depending on the valence of outcome, and whether stress alters the learning rate, i.e., how quickly information from the new environment is incorporated into choices. Participants were randomly assigned to either a stress or a control condition, and performed a two-stage Markov decision-making task in which the reward probabilities underwent periodic reversals without notice. We found that stress increased the contribution of model-free reinforcement learning only after negative outcome. Furthermore, stress decreased the learning rate. The results suggest that stress diminishes one’s ability to make adaptive choices in multiple aspects of reinforcement learning. This finding has implications for understanding how stress facilitates maladaptive habits, such as addictive behavior, and other dysfunctional behaviors associated with stress in clinical and educational contexts. PMID:28723943

Stress enhances model-free reinforcement learning only after negative outcome.

PubMed

Park, Heyeon; Lee, Daeyeol; Chey, Jeanyung

2017-01-01

Previous studies found that stress shifts behavioral control by promoting habits while decreasing goal-directed behaviors during reward-based decision-making. It is, however, unclear how stress disrupts the relative contribution of the two systems controlling reward-seeking behavior, i.e. model-free (or habit) and model-based (or goal-directed). Here, we investigated whether stress biases the contribution of model-free and model-based reinforcement learning processes differently depending on the valence of outcome, and whether stress alters the learning rate, i.e., how quickly information from the new environment is incorporated into choices. Participants were randomly assigned to either a stress or a control condition, and performed a two-stage Markov decision-making task in which the reward probabilities underwent periodic reversals without notice. We found that stress increased the contribution of model-free reinforcement learning only after negative outcome. Furthermore, stress decreased the learning rate. The results suggest that stress diminishes one's ability to make adaptive choices in multiple aspects of reinforcement learning. This finding has implications for understanding how stress facilitates maladaptive habits, such as addictive behavior, and other dysfunctional behaviors associated with stress in clinical and educational contexts.

Implicit chaining in cotton-top tamarins (Saguinus oedipus) with elements equated for probability of reinforcement

PubMed Central

Dillon, Laura; Collins, Meaghan; Conway, Maura; Cunningham, Kate

2013-01-01

Three experiments examined the implicit learning of sequences under conditions in which the elements comprising a sequence were equated in terms of reinforcement probability. In Experiment 1 cotton-top tamarins (Saguinus oedipus) experienced a five-element sequence displayed serially on a touch screen in which reinforcement probability was equated across elements at .16 per element. Tamarins demonstrated learning of this sequence with higher latencies during a random test as compared to baseline sequence training. In Experiments 2 and 3, manipulations of the procedure used in the first experiment were undertaken to rule out a confound owing to the fact that the elements in Experiment 1 bore different temporal relations to the intertrial interval (ITI), an inhibitory period. The results of Experiments 2 and 3 indicated that the implicit learning observed in Experiment 1 was not due to temporal proximity between some elements and the inhibitory ITI. The results taken together support two conclusion: First that tamarins engaged in sequence learning whether or not there was contingent reinforcement for learning the sequence, and second that this learning was not due to subtle differences in associative strength between the elements of the sequence. PMID:23344718

Improving the Science Excursion: An Educational Technologist's View

ERIC Educational Resources Information Center

Balson, M.

1973-01-01

Analyzes the nature of the learning process and attempts to show how the three components of a reinforcement contingency, the stimulus, the response and the reinforcement can be utilized to increase the efficiency of a typical science learning experience, the excursion. (JR)

Try P.R.A.I.S.E. - Positive Reinforcement And Individualized Systematic Economics.

ERIC Educational Resources Information Center

Wollam, Scott

Described is a multi-faceted money system which utilizes positive and negative reinforcement while at the same time incorporating peer pressure and reinforcement for behavior modification. The system uses such items as money, checks, deposit slips, and bank books. Children have jobs such as pencil sellers, banker, or door monitor, and receive pay…

Investigation of negative moment reinforcing in bridge decks.

DOT National Transportation Integrated Search

2015-09-01

Multi-span pre-tensioned pre-stressed concrete beam (PPCB) bridges made continuous usually experience a negative live load : moment region over the intermediate supports. Conventional thinking dictates that sufficient reinforcement must be provided i...

A corrosion monitoring system for existing reinforced concrete structures.

DOT National Transportation Integrated Search

2015-05-01

This study evaluated a multi-parameter corrosion monitoring system for existing reinforced concrete structures in chloride-laden service environments. The system was fabricated based on a prototype concrete corrosion measurement system that : had bee...

Gaze-contingent reinforcement learning reveals incentive value of social signals in young children and adults

PubMed Central

Smith, Tim J.; Senju, Atsushi

2017-01-01

While numerous studies have demonstrated that infants and adults preferentially orient to social stimuli, it remains unclear as to what drives such preferential orienting. It has been suggested that the learned association between social cues and subsequent reward delivery might shape such social orienting. Using a novel, spontaneous indication of reinforcement learning (with the use of a gaze contingent reward-learning task), we investigated whether children and adults' orienting towards social and non-social visual cues can be elicited by the association between participants' visual attention and a rewarding outcome. Critically, we assessed whether the engaging nature of the social cues influences the process of reinforcement learning. Both children and adults learned to orient more often to the visual cues associated with reward delivery, demonstrating that cue–reward association reinforced visual orienting. More importantly, when the reward-predictive cue was social and engaging, both children and adults learned the cue–reward association faster and more efficiently than when the reward-predictive cue was social but non-engaging. These new findings indicate that social engaging cues have a positive incentive value. This could possibly be because they usually coincide with positive outcomes in real life, which could partly drive the development of social orienting. PMID:28250186

Gaze-contingent reinforcement learning reveals incentive value of social signals in young children and adults.

PubMed

Vernetti, Angélina; Smith, Tim J; Senju, Atsushi

2017-03-15

While numerous studies have demonstrated that infants and adults preferentially orient to social stimuli, it remains unclear as to what drives such preferential orienting. It has been suggested that the learned association between social cues and subsequent reward delivery might shape such social orienting. Using a novel, spontaneous indication of reinforcement learning (with the use of a gaze contingent reward-learning task), we investigated whether children and adults' orienting towards social and non-social visual cues can be elicited by the association between participants' visual attention and a rewarding outcome. Critically, we assessed whether the engaging nature of the social cues influences the process of reinforcement learning. Both children and adults learned to orient more often to the visual cues associated with reward delivery, demonstrating that cue-reward association reinforced visual orienting. More importantly, when the reward-predictive cue was social and engaging, both children and adults learned the cue-reward association faster and more efficiently than when the reward-predictive cue was social but non-engaging. These new findings indicate that social engaging cues have a positive incentive value. This could possibly be because they usually coincide with positive outcomes in real life, which could partly drive the development of social orienting. © 2017 The Authors.

Learning and altering behaviours by reinforcement: neurocognitive differences between children and adults.

PubMed

Shephard, E; Jackson, G M; Groom, M J

2014-01-01

This study examined neurocognitive differences between children and adults in the ability to learn and adapt simple stimulus-response associations through feedback. Fourteen typically developing children (mean age=10.2) and 15 healthy adults (mean age=25.5) completed a simple task in which they learned to associate visually presented stimuli with manual responses based on performance feedback (acquisition phase), and then reversed and re-learned those associations following an unexpected change in reinforcement contingencies (reversal phase). Electrophysiological activity was recorded throughout task performance. We found no group differences in learning-related changes in performance (reaction time, accuracy) or in the amplitude of event-related potentials (ERPs) associated with stimulus processing (P3 ERP) or feedback processing (feedback-related negativity; FRN) during the acquisition phase. However, children's performance was significantly more disrupted by the reversal than adults and FRN amplitudes were significantly modulated by the reversal phase in children but not adults. These findings indicate that children have specific difficulties with reinforcement learning when acquired behaviours must be altered. This may be caused by the added demands on immature executive functioning, specifically response monitoring, created by the requirement to reverse the associations, or a developmental difference in the way in which children and adults approach reinforcement learning. Copyright © 2013 The Authors. Published by Elsevier Ltd.. All rights reserved.

Extension of Companion Modeling Using Classification Learning

NASA Astrophysics Data System (ADS)

Torii, Daisuke; Bousquet, François; Ishida, Toru

Companion Modeling is a methodology of refining initial models for understanding reality through a role-playing game (RPG) and a multiagent simulation. In this research, we propose a novel agent model construction methodology in which classification learning is applied to the RPG log data in Companion Modeling. This methodology enables a systematic model construction that handles multi-parameters, independent of the modelers ability. There are three problems in applying classification learning to the RPG log data: 1) It is difficult to gather enough data for the number of features because the cost of gathering data is high. 2) Noise data can affect the learning results because the amount of data may be insufficient. 3) The learning results should be explained as a human decision making model and should be recognized by the expert as being the result that reflects reality. We realized an agent model construction system using the following two approaches: 1) Using a feature selction method, the feature subset that has the best prediction accuracy is identified. In this process, the important features chosen by the expert are always included. 2) The expert eliminates irrelevant features from the learning results after evaluating the learning model through a visualization of the results. Finally, using the RPG log data from the Companion Modeling of agricultural economics in northeastern Thailand, we confirm the capability of this methodology.

Flow Navigation by Smart Microswimmers via Reinforcement Learning

NASA Astrophysics Data System (ADS)

Colabrese, Simona; Biferale, Luca; Celani, Antonio; Gustavsson, Kristian

2017-11-01

We have numerically modeled active particles which are able to acquire some limited knowledge of the fluid environment from simple mechanical cues and exert a control on their preferred steering direction. We show that those swimmers can learn effective strategies just by experience, using a reinforcement learning algorithm. As an example, we focus on smart gravitactic swimmers. These are active particles whose task is to reach the highest altitude within some time horizon, exploiting the underlying flow whenever possible. The reinforcement learning algorithm allows particles to learn effective strategies even in difficult situations when, in the absence of control, they would end up being trapped by flow structures. These strategies are highly nontrivial and cannot be easily guessed in advance. This work paves the way towards the engineering of smart microswimmers that solve difficult navigation problems. ERC AdG NewTURB 339032.

Distributed Learning, Extremum Seeking, and Model-Free Optimization for the Resilient Coordination of Multi-Agent Adversarial Groups

DTIC Science & Technology

2016-09-07

been demonstrated on maximum power point tracking for photovoltaic arrays and for wind turbines . 3. ES has recently been implemented on the Mars...high-dimensional optimization problems . Extensions and applications of these techniques were developed during the realization of the project. 15...studied problems of dynamic average consensus and a class of unconstrained continuous-time optimization algorithms for the coordination of multiple

A neural model of hierarchical reinforcement learning.

PubMed

Rasmussen, Daniel; Voelker, Aaron; Eliasmith, Chris

2017-01-01

We develop a novel, biologically detailed neural model of reinforcement learning (RL) processes in the brain. This model incorporates a broad range of biological features that pose challenges to neural RL, such as temporally extended action sequences, continuous environments involving unknown time delays, and noisy/imprecise computations. Most significantly, we expand the model into the realm of hierarchical reinforcement learning (HRL), which divides the RL process into a hierarchy of actions at different levels of abstraction. Here we implement all the major components of HRL in a neural model that captures a variety of known anatomical and physiological properties of the brain. We demonstrate the performance of the model in a range of different environments, in order to emphasize the aim of understanding the brain's general reinforcement learning ability. These results show that the model compares well to previous modelling work and demonstrates improved performance as a result of its hierarchical ability. We also show that the model's behaviour is consistent with available data on human hierarchical RL, and generate several novel predictions.

Neural correlates of reinforcement learning and social preferences in competitive bidding.

PubMed

van den Bos, Wouter; Talwar, Arjun; McClure, Samuel M

2013-01-30

In competitive social environments, people often deviate from what rational choice theory prescribes, resulting in losses or suboptimal monetary gains. We investigate how competition affects learning and decision-making in a common value auction task. During the experiment, groups of five human participants were simultaneously scanned using MRI while playing the auction task. We first demonstrate that bidding is well characterized by reinforcement learning with biased reward representations dependent on social preferences. Indicative of reinforcement learning, we found that estimated trial-by-trial prediction errors correlated with activity in the striatum and ventromedial prefrontal cortex. Additionally, we found that individual differences in social preferences were related to activity in the temporal-parietal junction and anterior insula. Connectivity analyses suggest that monetary and social value signals are integrated in the ventromedial prefrontal cortex and striatum. Based on these results, we argue for a novel mechanistic account for the integration of reinforcement history and social preferences in competitive decision-making.

Attentional Selection Can Be Predicted by Reinforcement Learning of Task-relevant Stimulus Features Weighted by Value-independent Stickiness.

PubMed

Balcarras, Matthew; Ardid, Salva; Kaping, Daniel; Everling, Stefan; Womelsdorf, Thilo

2016-02-01

Attention includes processes that evaluate stimuli relevance, select the most relevant stimulus against less relevant stimuli, and bias choice behavior toward the selected information. It is not clear how these processes interact. Here, we captured these processes in a reinforcement learning framework applied to a feature-based attention task that required macaques to learn and update the value of stimulus features while ignoring nonrelevant sensory features, locations, and action plans. We found that value-based reinforcement learning mechanisms could account for feature-based attentional selection and choice behavior but required a value-independent stickiness selection process to explain selection errors while at asymptotic behavior. By comparing different reinforcement learning schemes, we found that trial-by-trial selections were best predicted by a model that only represents expected values for the task-relevant feature dimension, with nonrelevant stimulus features and action plans having only a marginal influence on covert selections. These findings show that attentional control subprocesses can be described by (1) the reinforcement learning of feature values within a restricted feature space that excludes irrelevant feature dimensions, (2) a stochastic selection process on feature-specific value representations, and (3) value-independent stickiness toward previous feature selections akin to perseveration in the motor domain. We speculate that these three mechanisms are implemented by distinct but interacting brain circuits and that the proposed formal account of feature-based stimulus selection will be important to understand how attentional subprocesses are implemented in primate brain networks.

Synthesis and Characterization of Multi Wall Carbon Nanotubes (MWCNT) Reinforced Sintered Magnesium Matrix Composites

NASA Astrophysics Data System (ADS)

Vijaya Bhaskar, S.; Rajmohan, T.; Palanikumar, K.; Bharath Ganesh Kumar, B.

2016-04-01

Metal matrix composites (MMCs) reinforced with ceramic nano particles (less than 100 nm), termed as metal matrix nano composites (MMNCs), can overcome those disadvantages associated with the conventional MMCs. MMCs containing carbon nanotubes are being developed and projected for diverse applications in various fields of engineering like automotive, avionic, electronic and bio-medical sectors. The present investigation deals with the synthesis and characterization of hybrid magnesium matrix reinforced with various different wt% (0-0.45) of multi wall carbon nano tubes (MWCNT) and micro SiC particles prepared through powder metallurgy route. Microstructure and mechanical properties such as micro hardness and density of the composites were examined. Microstructure of MMNCs have been investigated by scanning electron microscope, X-ray diffraction and energy dispersive X-ray spectroscopy (EDS) for better observation of dispersion of reinforcement. The results indicated that the increase in wt% of MWCNT improves the mechanical properties of the composite.

Multi-Scale Microstructure and Mechanical Properties of High Carbon Eutectic Tantalum Carbide Reinforced with Carbon Nanotubes

DTIC Science & Technology

2012-07-02

more effective grain growth inhibitors. Transverse Rupture Strength of TaC reinforced with shorter CNTs displayed highest strength/density ratio with...microstructural features. 6. Strength to density ratio of CNT reinforced TaC increased from 17 to 28, which is an increase of ~ 65%. 7. Oxidation behavior of... reinforced with carbon fibers for space applications [15,16]. In recent years, Spark Plasma Sintering (SPS) also known as Electric Field Assisted Sintering

Extinction of Pavlovian conditioning: The influence of trial number and reinforcement history.

PubMed

Chan, C K J; Harris, Justin A

2017-08-01

Pavlovian conditioning is sensitive to the temporal relationship between the conditioned stimulus (CS) and the unconditioned stimulus (US). This has motivated models that describe learning as a process that continuously updates associative strength during the trial or specifically encodes the CS-US interval. These models predict that extinction of responding is also continuous, such that response loss is proportional to the cumulative duration of exposure to the CS without the US. We review evidence showing that this prediction is incorrect, and that extinction is trial-based rather than time-based. We also present two experiments that test the importance of trials versus time on the Partial Reinforcement Extinction Effect (PREE), in which responding extinguishes more slowly for a CS that was inconsistently reinforced with the US than for a consistently reinforced one. We show that increasing the number of extinction trials of the partially reinforced CS, relative to the consistently reinforced CS, overcomes the PREE. However, increasing the duration of extinction trials by the same amount does not overcome the PREE. We conclude that animals learn about the likelihood of the US per trial during conditioning, and learn trial-by-trial about the absence of the US during extinction. Moreover, what they learn about the likelihood of the US during conditioning affects how sensitive they are to the absence of the US during extinction. Copyright © 2017 Elsevier B.V. All rights reserved.

Assessment of Material Solutions of Multi-level Garage Structure Within Integrated Life Cycle Design Process

NASA Astrophysics Data System (ADS)

Wałach, Daniel; Sagan, Joanna; Gicala, Magdalena

2017-10-01

The paper presents an environmental and economic analysis of the material solutions of multi-level garage. The construction project approach considered reinforced concrete structure under conditions of use of ordinary concrete and high-performance concrete (HPC). Using of HPC allowed to significant reduction of reinforcement steel, mainly in compression elements (columns) in the construction of the object. The analysis includes elements of the methodology of integrated lice cycle design (ILCD). By making multi-criteria analysis based on established weight of the economic and environmental parameters, three solutions have been evaluated and compared within phase of material production (information modules A1-A3).

Can Service Learning Reinforce Social and Cultural Bias? Exploring a Popular Model of Family Involvement for Early Childhood Teacher Candidates

ERIC Educational Resources Information Center

Dunn-Kenney, Maylan

2010-01-01

Service learning is often used in teacher education as a way to challenge social bias and provide teacher candidates with skills needed to work in partnership with diverse families. Although some literature suggests that service learning could reinforce cultural bias, there is little documentation. In a study of 21 early childhood teacher…

Deep Gate Recurrent Neural Network

DTIC Science & Technology

2016-11-22

Schmidhuber. A system for robotic heart surgery that learns to tie knots using recurrent neural networks. In IEEE International Conference on...tasks, such as Machine Translation (Bahdanau et al. (2015)) or Robot Reinforcement Learning (Bakker (2001)). The main idea behind these networks is to...and J. Peters. Reinforcement learning in robotics : A survey. The International Journal of Robotics Research, 32:1238–1274, 2013. ISSN 0278-3649. doi

Low-Cost Nanocellulose-Reinforced High-Temperature Polymer Composites for Additive Manufacturing

DOE Office of Scientific and Technical Information (OSTI.GOV)

Ozcan, Soydan; Tekinalp, Halil L.; Love, Lonnie J.

2016-07-13

ORNL worked with American Process Inc. to demonstrate the potential use of bio-based BioPlus ® lignin-coated cellulose nanofibrils (L-CNF) as a reinforcing agent in the development of polymer feedstock suitable for additive manufacturing. L-CNF-reinforced polylactic acid (PLA) testing coupons were prepared and up to 69% increase in tensile strength and 133% increase in elastic modulus were demonstrated.

The role of family planning communications--an agent of reinforcement or change.

PubMed

Chen, E C

1981-12-01

Results are presented of a multiple classification analysis of responses to a 1972 KAP survey in Taiwan of 2013 married women aged 18-34 designed to determine whether family planning communication is primarily a reinforcement agent or a change agent. 2 types of independent variables, social demographic variables including age, number of children, residence, education, employment status, and duration of marriage; and social climate variables including ever receiving family planning information from mass media and ever discussing family planning with others, were used. KAP levels, the dependent variables, were measured by 2 variables each: awareness of effective methods and awareness of government supply of contraceptives for knowledge, wish for additional children and approve of 2-child family for attitude, and never use contraception and neither want children nor use contraception for practice. Social demographic and attitudinal variables were found to be the critical ones, while social climate and knowledge variables had only negligible effects on various stages of family planning adoption, indicating that family planning communications functioned primarily as a reinforcement agent. The effects of social demographic variables were prominent in all stages of contraceptive adoption. Examination of effects of individual variables on various stages of family planning adoption still supported the argument that family planning communications played a reinforcement role. Family planning communications functioned well in diffusing family planning knowledge and accessibility, but social demographic variables and desire for additional children were the most decisive influences on use of contraception.

Fire performance, microstructure and thermal degradation of an epoxy based nano intumescent fire retardant coating for structural applications

DOE Office of Scientific and Technical Information (OSTI.GOV)

Aziz, Hammad, E-mail: engr.hammad.aziz03@gmail.com; Ahmad, Faiz, E-mail: faizahmad@petronas.com.my; Yusoff, P. S. M. Megat

Intumescent fire retardant coating (IFRC) is a passive fire protection system which swells upon heating to form expanded multi-cellular char layer that protects the substrate from fire. In this research work, IFRC’s were developed using different flame retardants such as ammonium polyphosphate, expandable graphite, melamine and boric acid. These flame retardants were bound together with the help of epoxy binder and cured together using curing agent. IFRC was then reinforced with nano magnesium oxide and nano alumina as inorganic fillers to study their effect towards fire performance, microstructure and thermal degradation. Small scale fire test was conducted to investigate themore » thermal insulation of coating whereas fire performance was calculated using thermal margin value. Field emission scanning electron microscopy was used to examine the microstructure of char obtained after fire test. Thermogravimetric analysis was conducted to investigate the residual weight of coating. Results showed that the performance of the coating was enhanced by reinforcement with nano size fillers as compared to non-filler based coating. Comparing both nano size magnesium oxide and nano size alumina; nano size alumina gave better fire performance with improved microstructure of char and high residual weight.« less

Fire performance, microstructure and thermal degradation of an epoxy based nano intumescent fire retardant coating for structural applications

NASA Astrophysics Data System (ADS)

Aziz, Hammad; Ahmad, Faiz; Yusoff, P. S. M. Megat; Zia-ul-Mustafa, M.

2015-07-01

Intumescent fire retardant coating (IFRC) is a passive fire protection system which swells upon heating to form expanded multi-cellular char layer that protects the substrate from fire. In this research work, IFRC's were developed using different flame retardants such as ammonium polyphosphate, expandable graphite, melamine and boric acid. These flame retardants were bound together with the help of epoxy binder and cured together using curing agent. IFRC was then reinforced with nano magnesium oxide and nano alumina as inorganic fillers to study their effect towards fire performance, microstructure and thermal degradation. Small scale fire test was conducted to investigate the thermal insulation of coating whereas fire performance was calculated using thermal margin value. Field emission scanning electron microscopy was used to examine the microstructure of char obtained after fire test. Thermogravimetric analysis was conducted to investigate the residual weight of coating. Results showed that the performance of the coating was enhanced by reinforcement with nano size fillers as compared to non-filler based coating. Comparing both nano size magnesium oxide and nano size alumina; nano size alumina gave better fire performance with improved microstructure of char and high residual weight.

Evaluation of Graduated vs All-or-None Contingencies on Rate Tasks for Individuals Diagnosed with Autism

ERIC Educational Resources Information Center

Kassardjian, Alyne; Leaf, Jeremy A.; Leaf, Justin B.; Townley-Cochran, Donna; Alcalay, Aditt; Milne, Christine; Dale, Stephanie; Tsuji, Kathleen; Leaf, Ronald; Taubman, Mitchell; McEachin, John

2016-01-01

The graduated reinforcement procedure (also known as differential reinforcement) is an often-used procedure in the field of Applied Behavior Analysis to teach new skills and increase pro-social behaviors. In this study, the researchers used a multi-element design to evaluated the graduated reinforcement procedure for six children with a diagnosis…

Prediction of anti-cancer drug response by kernelized multi-task learning.

PubMed

Tan, Mehmet

2016-10-01

Chemotherapy or targeted therapy are two of the main treatment options for many types of cancer. Due to the heterogeneous nature of cancer, the success of the therapeutic agents differs among patients. In this sense, determination of chemotherapeutic response of the malign cells is essential for establishing a personalized treatment protocol and designing new drugs. With the recent technological advances in producing large amounts of pharmacogenomic data, in silico methods have become important tools to achieve this aim. Data produced by using cancer cell lines provide a test bed for machine learning algorithms that try to predict the response of cancer cells to different agents. The potential use of these algorithms in drug discovery/repositioning and personalized treatments motivated us in this study to work on predicting drug response by exploiting the recent pharmacogenomic databases. We aim to improve the prediction of drug response of cancer cell lines. We propose to use a method that employs multi-task learning to improve learning by transfer, and kernels to extract non-linear relationships to predict drug response. The method outperforms three state-of-the-art algorithms on three anti-cancer drug screen datasets. We achieved a mean squared error of 3.305 and 0.501 on two different large scale screen data sets. On a recent challenge dataset, we obtained an error of 0.556. We report the methodological comparison results as well as the performance of the proposed algorithm on each single drug. The results show that the proposed method is a strong candidate to predict drug response of cancer cell lines in silico for pre-clinical studies. The source code of the algorithm and data used can be obtained from http://mtan.etu.edu.tr/Supplementary/kMTrace/. Copyright © 2016 Elsevier B.V. All rights reserved.

Conceptualizing withdrawal-induced escalation of alcohol self-administration as a learned, plasticity-dependent process

PubMed Central

Walker, Brendan M.

2013-01-01

This article represents one of five contributions focusing on the topic “Plasticity and neuroadaptive responses within the extended amygdala in response to chronic or excessive alcohol exposure” that were developed by awardees participating in the Young Investigator Award Symposium at the “Alcoholism and Stress: A Framework for Future Treatment Strategies” conference in Volterra, Italy on May 3–6, 2011 that was organized/chaired by Drs. Antonio Noronha and Fulton Crews and sponsored by the National Institute on Alcohol Abuse and Alcoholism. This review discusses the dependence-induced neuroadaptations in affective systems that provide a basis for negative reinforcement learning and presents evidence demonstrating that escalated alcohol consumption during withdrawal is a learned, plasticity-dependent process. The review concludes by identifying changes within extended amygdala dynorphin/kappa-opioid receptor systems that could serve as the foundation for the occurrence of negative reinforcement processes. While some evidence contained herein may be specific to alcohol dependence-related learning and plasticity, much of the information will be of relevance to any addictive disorder involving negative reinforcement mechanisms. Collectively, the information presented within this review provides a framework to assess the negative reinforcing effects of alcohol in a manner that distinguishes neuroadaptations produced by chronic alcohol exposure from the actual plasticity that is associated with negative reinforcement learning in dependent organisms. PMID:22459874

Reinforcement Learning Strategies for Clinical Trials in Non-small Cell Lung Cancer

PubMed Central

Zhao, Yufan; Zeng, Donglin; Socinski, Mark A.; Kosorok, Michael R.

2010-01-01

Summary Typical regimens for advanced metastatic stage IIIB/IV non-small cell lung cancer (NSCLC) consist of multiple lines of treatment. We present an adaptive reinforcement learning approach to discover optimal individualized treatment regimens from a specially designed clinical trial (a “clinical reinforcement trial”) of an experimental treatment for patients with advanced NSCLC who have not been treated previously with systemic therapy. In addition to the complexity of the problem of selecting optimal compounds for first and second-line treatments based on prognostic factors, another primary goal is to determine the optimal time to initiate second-line therapy, either immediately or delayed after induction therapy, yielding the longest overall survival time. A reinforcement learning method called Q-learning is utilized which involves learning an optimal regimen from patient data generated from the clinical reinforcement trial. Approximating the Q-function with time-indexed parameters can be achieved by using a modification of support vector regression which can utilize censored data. Within this framework, a simulation study shows that the procedure can extract optimal regimens for two lines of treatment directly from clinical data without prior knowledge of the treatment effect mechanism. In addition, we demonstrate that the design reliably selects the best initial time for second-line therapy while taking into account the heterogeneity of NSCLC across patients. PMID:21385164

Serotonergic antidepressants decrease hedonic signals but leave learning signals in the nucleus accumbens unaffected.

PubMed

Graf, Heiko; Metzger, Coraline D; Walter, Martin; Abler, Birgit

2016-01-06

Investigating the effects of serotonergic antidepressants on neural correlates of visual erotic stimulation revealed decreased reactivity within the dopaminergic reward network along with decreased subjective sexual functioning compared with placebo. However, a global dampening of the reward system under serotonergic drugs is not intuitive considering clinical observations of their beneficial effects in the treatment of depression. Particularly, learning signals as coded in prediction error processing within the dopaminergic reward system can be assumed to be rather enhanced as antidepressant drugs have been demonstrated to facilitate the efficacy of psychotherapeutic interventions relying on learning processes. Within the same study sample, we now explored the effects of serotonergic and dopaminergic/noradrenergic antidepressants on prediction error signals compared with placebo by functional MRI. A total of 17 healthy male participants (mean age: 25.4 years) were investigated under the administration of paroxetine, bupropion and placebo for 7 days each within a randomized, double-blind, within-subject cross-over design. During functional MRI, we used an established monetary incentive task to explore neural prediction error signals within the bilateral nucleus accumbens as region of interest within the dopaminergic reward system. In contrast to diminished neural activations and subjective sexual functioning under the serotonergic agent paroxetine under visual erotic stimulation, we revealed unaffected or even enhanced neural prediction error processing within the nucleus accumbens under this antidepressant along with unaffected behavioural processing. Our study provides evidence that serotonergic antidepressants facilitate prediction error signalling and may support suggestions of beneficial effects of these agents on reinforced learning as an essential element in behavioural psychotherapy.

Interaction with Machine Improvisation

NASA Astrophysics Data System (ADS)

Assayag, Gerard; Bloch, George; Cont, Arshia; Dubnov, Shlomo

We describe two multi-agent architectures for an improvisation oriented musician-machine interaction systems that learn in real time from human performers. The improvisation kernel is based on sequence modeling and statistical learning. We present two frameworks of interaction with this kernel. In the first, the stylistic interaction is guided by a human operator in front of an interactive computer environment. In the second framework, the stylistic interaction is delegated to machine intelligence and therefore, knowledge propagation and decision are taken care of by the computer alone. The first framework involves a hybrid architecture using two popular composition/performance environments, Max and OpenMusic, that are put to work and communicate together, each one handling the process at a different time/memory scale. The second framework shares the same representational schemes with the first but uses an Active Learning architecture based on collaborative, competitive and memory-based learning to handle stylistic interactions. Both systems are capable of processing real-time audio/video as well as MIDI. After discussing the general cognitive background of improvisation practices, the statistical modelling tools and the concurrent agent architecture are presented. Then, an Active Learning scheme is described and considered in terms of using different improvisation regimes for improvisation planning. Finally, we provide more details about the different system implementations and describe several performances with the system.

Using an online quiz-based reinforcement system to teach healthcare quality and patient safety and care transitions at the University of California.

PubMed

Shaikh, Ulfat; Afsar-Manesh, Nasim; Amin, Alpesh N; Clay, Brian; Ranji, Sumant R

2017-10-01

Implementing quality improvement (QI) education during clinical training is challenging due to time constraints and inadequate faculty development in these areas. Quiz-based reinforcement systems show promise in fostering active engagement, collaboration, healthy competition and real-time formative feedback, although further research on their effectiveness is required. An online quiz-based reinforcement system to increase resident and faculty knowledge in QI, patient safety and care transitions. Experts in QI and educational assessment at the 5 University of California medical campuses developed a course comprised of 3 quizzes on Introduction to QI, Patient Safety and Care Transitions. Each quiz contained 20 questions and utilized an online educational quiz-based reinforcement system that leveraged spaced learning. Approximately 500 learners completed the course (completion rate 66-86%). Knowledge acquisition scores for all quizzes increased after completion: Introduction to QI (35-73%), Patient Safety (58-95%), and Care Transitions (66-90%). Learners reported that the quiz-based system was an effective teaching modality and preferred this type of education to classroom-based lectures. Suggestions for improvement included reducing frequency of presentation of questions and utilizing more questions that test learners on application of knowledge instead of knowledge acquisition. A multi-campus online quiz-based reinforcement system to train residents in QI, patient safety and care transitions was feasible, acceptable, and increased knowledge. The course may be best utilized to supplement classroom-based and experiential curricula, along with increased attention to optimizing frequency of presentation of questions and enhancing application skills. © The Author 2017. Published by Oxford University Press in association with the International Society for Quality in Health Care. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com

Depression, Activity, and Evaluation of Reinforcement

ERIC Educational Resources Information Center

Hammen, Constance L.; Glass, David R., Jr.

1975-01-01

This research attempted to find the causal relation between mood and level of reinforcement. An effort was made to learn what mood change might occur if depressed subjects increased their levels of participation in reinforcing activities. (Author/RK)

Kinesthetic Reinforcement-Is It a Boon to Learning?

ERIC Educational Resources Information Center

Bohrer, Roxilu K.

1970-01-01

Language instruction, particularly in the elementary school, should be reinforced through the use of visual aids and through associated physical activity. Kinesthetic experiences provide an opportunity to make use of non-verbal cues to meaning, enliven classroom activities, and maximize learning for pupils. The author discusses the educational…

Reinforcing Basic Skills Through Social Studies. Grades 4-7.

ERIC Educational Resources Information Center

Lewis, Teresa Marie

Arranged into seven parts, this document provides a variety of games and activities, bulletin board ideas, overhead transparencies, student handouts, and learning station ideas to help reinforce basic social studies skills in the intermediate grades. In part 1, students learn about timelines, first constructing their own life timeline, then a…

Effects of Reinforcement on Peer Imitation in a Small Group Play Context

ERIC Educational Resources Information Center

Barton, Erin E.; Ledford, Jennifer R.

2018-01-01

Children with disabilities often have deficits in imitation skills, particularly in imitating peers. Imitation is considered a behavioral cusp--which, once learned, allows a child to access additional and previously unavailable learning opportunities. In the current study, researchers examined the efficacy of contingent reinforcement delivered…

Neurofeedback in Learning Disabled Children: Visual versus Auditory Reinforcement.

PubMed

Fernández, Thalía; Bosch-Bayard, Jorge; Harmony, Thalía; Caballero, María I; Díaz-Comas, Lourdes; Galán, Lídice; Ricardo-Garcell, Josefina; Aubert, Eduardo; Otero-Ojeda, Gloria

2016-03-01

Children with learning disabilities (LD) frequently have an EEG characterized by an excess of theta and a deficit of alpha activities. NFB using an auditory stimulus as reinforcer has proven to be a useful tool to treat LD children by positively reinforcing decreases of the theta/alpha ratio. The aim of the present study was to optimize the NFB procedure by comparing the efficacy of visual (with eyes open) versus auditory (with eyes closed) reinforcers. Twenty LD children with an abnormally high theta/alpha ratio were randomly assigned to the Auditory or the Visual group, where a 500 Hz tone or a visual stimulus (a white square), respectively, was used as a positive reinforcer when the value of the theta/alpha ratio was reduced. Both groups had signs consistent with EEG maturation, but only the Auditory Group showed behavioral/cognitive improvements. In conclusion, the auditory reinforcer was more efficacious in reducing the theta/alpha ratio, and it improved the cognitive abilities more than the visual reinforcer.

Effect of Silane Coupling Agent on Tribological Properties of Hemp Fiber-Reinforced Plant-Derived Polyamide 1010 Biomass Composites

PubMed Central

Kajiyama, Tetsuto; Yamanaka, Toshiyuki

2017-01-01

We have studied the effects of silane coupling agents used for the surface treatment of fiber on the tribological properties of hemp fiber (HF) reinforced plant-derived polyamide 1010 (PA1010) biomass composites. Hemp fibers were surface-treated by two surface treatment methods: (a) alkali treatment by sodium hydroxide solution and (b) surface treatment by silane coupling agents. Three types of silane coupling agents, namely aminosilane, epoxysilane and ureidosilane were used. These HF/PA1010 biomass composites were extruded using a twin extruder, and injection-molded. The mechanical and tribological properties were evaluated by the ring-on-plate type sliding wear test. It was found that tribological properties of HF/PA1010 biomass composites improved with the surface treatment by the silane coupling agent. This may be attributed to the change in the mode of friction and wear mechanism by the interfacial adhesion between fiber and matrix polymer according to the type of silane coupling agent used. In particular, the ureidosilane coupling agent showed the best improvement effect for the tribological properties of these biomass composites in this study. PMID:28872624

Model of interaction in Smart Grid on the basis of multi-agent system

NASA Astrophysics Data System (ADS)

Engel, E. A.; Kovalev, I. V.; Engel, N. E.

2016-11-01

This paper presents model of interaction in Smart Grid on the basis of multi-agent system. The use of travelling waves in the multi-agent system describes the behavior of the Smart Grid from the local point, which is being the complement of the conventional approach. The simulation results show that the absorption of the wave in the distributed multi-agent systems is effectively simulated the interaction in Smart Grid.

Cytotoxicity of silica-glass fiber reinforced composites.

PubMed

Meriç, Gökçe; Dahl, Jon E; Ruyter, I Eystein

2008-09-01

Silica-glass fiber reinforced polymers can be used for many kinds of dental applications. The fiber reinforcement enhances the mechanical properties of the polymers, and they have good esthetic attributes. There is good initial bonding of glass fibers to polymers via an interface made from silane coupling agents. The aim of this in vitro study was to determine the cytotoxicity of two polymers reinforced with two differently sized silica-glass fibers before and after thermal cycling. Cytotoxicity of the polymers without fibers was also evaluated. Two different resin mixtures (A and B) were prepared from poly(vinyl chloridecovinylacetate) powder and poly(methyl methacrylate) (PMMA) dissolved in methyl methacrylate and mixed with different cross-linking agents. The resin A contained the cross-linking agents ethylene glycol dimethacrylate and 1,4-butanediol dimethacrylate, and for resin B diethylene glycol dimethacrylate was used. Woven silica-glass fibers were used for reinforcement. The fibers were sized with either linear poly(butyl methacrylate)-sizing or cross-linking PMMA-sizing. Cytotoxicity was evaluated by filter diffusion test (ISO 7405:1997) of newly made and thermocycled test specimens. Extracts were prepared according to ISO 10993-12 from newly made and from thermocycled specimens and tested by the MTT assay. The results from the experiments were statistically analyzed by one-way ANOVA and Tukey's test (rho<0.05). The filter diffusion test disclosed no change in staining intensity at the cell-test sample contact area indicating non-cytotoxicity in all experimental groups. Cell viability assessed by MTT assay was more than 90% in all experimental groups. All are non-cytotoxic. It can be concluded that correctly processed heat polymerized silica-glass fiber reinforced polymers induced no cytotoxicity and that thermocycling did not alter this property.

The probability of reinforcement per trial affects posttrial responding and subsequent extinction but not within-trial responding.

PubMed

Harris, Justin A; Kwok, Dorothy W S

2018-01-01

During magazine approach conditioning, rats do not discriminate between a conditional stimulus (CS) that is consistently reinforced with food and a CS that is occasionally (partially) reinforced, as long as the CSs have the same overall reinforcement rate per second. This implies that rats are indifferent to the probability of reinforcement per trial. However, in the same rats, the per-trial reinforcement rate will affect subsequent extinction-responding extinguishes more rapidly for a CS that was consistently reinforced than for a partially reinforced CS. Here, we trained rats with consistently and partially reinforced CSs that were matched for overall reinforcement rate per second. We measured conditioned responding both during and immediately after the CSs. Differences in the per-trial probability of reinforcement did not affect the acquisition of responding during the CS but did affect subsequent extinction of that responding, and also affected the post-CS response rates during conditioning. Indeed, CSs with the same probability of reinforcement per trial evoked the same amount of post-CS responding even when they differed in overall reinforcement rate and thus evoked different amounts of responding during the CS. We conclude that reinforcement rate per second controls rats' acquisition of responding during the CS, but at the same time, rats also learn specifically about the probability of reinforcement per trial. The latter learning affects the rats' expectation of reinforcement as an outcome of the trial, which influences their ability to detect retrospectively that an opportunity for reinforcement was missed, and, in turn, drives extinction. (PsycINFO Database Record (c) 2018 APA, all rights reserved).

Establishment and Maintenance of Socially Learned Conditioned Reinforcement in Young Children: Elimination of the Role of Adults and View of Peers' Faces

ERIC Educational Resources Information Center

Zrinzo, Michelle; Greer, R. Douglas

2013-01-01

Prior research has demonstrated the establishment of reinforcers for learning and maintenance with young children as a function of social learning where a peer and an adult experimenter were present. The presence of an adult experimenter was eliminated in the present study to test if the effect produced in the prior studies would occur with only…

Structure identification in fuzzy inference using reinforcement learning

NASA Technical Reports Server (NTRS)

Berenji, Hamid R.; Khedkar, Pratap

1993-01-01

In our previous work on the GARIC architecture, we have shown that the system can start with surface structure of the knowledge base (i.e., the linguistic expression of the rules) and learn the deep structure (i.e., the fuzzy membership functions of the labels used in the rules) by using reinforcement learning. Assuming the surface structure, GARIC refines the fuzzy membership functions used in the consequents of the rules using a gradient descent procedure. This hybrid fuzzy logic and reinforcement learning approach can learn to balance a cart-pole system and to backup a truck to its docking location after a few trials. In this paper, we discuss how to do structure identification using reinforcement learning in fuzzy inference systems. This involves identifying both surface as well as deep structure of the knowledge base. The term set of fuzzy linguistic labels used in describing the values of each control variable must be derived. In this process, splitting a label refers to creating new labels which are more granular than the original label and merging two labels creates a more general label. Splitting and merging of labels directly transform the structure of the action selection network used in GARIC by increasing or decreasing the number of hidden layer nodes.

Spared internal but impaired external reward prediction error signals in major depressive disorder during reinforcement learning.

PubMed

Bakic, Jasmina; Pourtois, Gilles; Jepma, Marieke; Duprat, Romain; De Raedt, Rudi; Baeken, Chris

2017-01-01

Major depressive disorder (MDD) creates debilitating effects on a wide range of cognitive functions, including reinforcement learning (RL). In this study, we sought to assess whether reward processing as such, or alternatively the complex interplay between motivation and reward might potentially account for the abnormal reward-based learning in MDD. A total of 35 treatment resistant MDD patients and 44 age matched healthy controls (HCs) performed a standard probabilistic learning task. RL was titrated using behavioral, computational modeling and event-related brain potentials (ERPs) data. MDD patients showed comparable learning rate compared to HCs. However, they showed decreased lose-shift responses as well as blunted subjective evaluations of the reinforcers used during the task, relative to HCs. Moreover, MDD patients showed normal internal (at the level of error-related negativity, ERN) but abnormal external (at the level of feedback-related negativity, FRN) reward prediction error (RPE) signals during RL, selectively when additional efforts had to be made to establish learning. Collectively, these results lend support to the assumption that MDD does not impair reward processing per se during RL. Instead, it seems to alter the processing of the emotional value of (external) reinforcers during RL, when additional intrinsic motivational processes have to be engaged. © 2016 Wiley Periodicals, Inc.

Knowledge-based personalized search engine for the Web-based Human Musculoskeletal System Resources (HMSR) in biomechanics.

PubMed

Dao, Tien Tuan; Hoang, Tuan Nha; Ta, Xuan Hien; Tho, Marie Christine Ho Ba

2013-02-01

Human musculoskeletal system resources of the human body are valuable for the learning and medical purposes. Internet-based information from conventional search engines such as Google or Yahoo cannot response to the need of useful, accurate, reliable and good-quality human musculoskeletal resources related to medical processes, pathological knowledge and practical expertise. In this present work, an advanced knowledge-based personalized search engine was developed. Our search engine was based on a client-server multi-layer multi-agent architecture and the principle of semantic web services to acquire dynamically accurate and reliable HMSR information by a semantic processing and visualization approach. A security-enhanced mechanism was applied to protect the medical information. A multi-agent crawler was implemented to develop a content-based database of HMSR information. A new semantic-based PageRank score with related mathematical formulas were also defined and implemented. As the results, semantic web service descriptions were presented in OWL, WSDL and OWL-S formats. Operational scenarios with related web-based interfaces for personal computers and mobile devices were presented and analyzed. Functional comparison between our knowledge-based search engine, a conventional search engine and a semantic search engine showed the originality and the robustness of our knowledge-based personalized search engine. In fact, our knowledge-based personalized search engine allows different users such as orthopedic patient and experts or healthcare system managers or medical students to access remotely into useful, accurate, reliable and good-quality HMSR information for their learning and medical purposes. Copyright © 2012 Elsevier Inc. All rights reserved.

Relationship between Reinforcement and Eye Movements during Ocular Motor Training with Learning Disabled Children.

ERIC Educational Resources Information Center

Punnett, Audrey F.; Steinhauer, Gene D.

1984-01-01

Four reading disabled children were given eight sessions of ocular motor training with reinforcement and eight sessions without reinforcement. Two reading disabled control Ss were treated similarly but received no ocular motor training. Results demonstrated that reinforcement can improve ocular motor skills, which in turn elevates reading…

Learning the specific quality of taste reinforcement in larval Drosophila.

PubMed

Schleyer, Michael; Miura, Daisuke; Tanimura, Teiichi; Gerber, Bertram

2015-01-27

The only property of reinforcement insects are commonly thought to learn about is its value. We show that larval Drosophila not only remember the value of reinforcement (How much?), but also its quality (What?). This is demonstrated both within the appetitive domain by using sugar vs amino acid as different reward qualities, and within the aversive domain by using bitter vs high-concentration salt as different qualities of punishment. From the available literature, such nuanced memories for the quality of reinforcement are unexpected and pose a challenge to present models of how insect memory is organized. Given that animals as simple as larval Drosophila, endowed with but 10,000 neurons, operate with both reinforcement value and quality, we suggest that both are fundamental aspects of mnemonic processing-in any brain.

The partial-reinforcement extinction effect and the contingent-sampling hypothesis.

PubMed

Hochman, Guy; Erev, Ido

2013-12-01

The partial-reinforcement extinction effect (PREE) implies that learning under partial reinforcements is more robust than learning under full reinforcements. While the advantages of partial reinforcements have been well-documented in laboratory studies, field research has failed to support this prediction. In the present study, we aimed to clarify this pattern. Experiment 1 showed that partial reinforcements increase the tendency to select the promoted option during extinction; however, this effect is much smaller than the negative effect of partial reinforcements on the tendency to select the promoted option during the training phase. Experiment 2 demonstrated that the overall effect of partial reinforcements varies inversely with the attractiveness of the alternative to the promoted behavior: The overall effect is negative when the alternative is relatively attractive, and positive when the alternative is relatively unattractive. These results can be captured with a contingent-sampling model assuming that people select options that provided the best payoff in similar past experiences. The best fit was obtained under the assumption that similarity is defined by the sequence of the last four outcomes.