Vai al contenuto principale della pagina

Reinforcement learning : state-of-the-art / Marco Wiering and Martijn van Otterlo (eds.).



(Visualizza formato Marc21)    (visualizza in BIBRAME 2.0)

Creatore:
Titolo: Reinforcement learning : state-of-the-art / Marco Wiering and Martijn van Otterlo (eds.).
Link to work: Reinforcement learning Visualizza cluster
Pubblicazione: Berlin ; New York : Springer, ©2012
Estensione: 1 online resource (xxxiv, 638 pages).
Tipo formato: computer
Tipo contenuto: text
Tipo supporto: online resource
Disciplina: 006.3/1
Titolo uniforme di collana: Adaptation, learning and optimization ; v. 12.
Genere/Forma: Electronic books
Index term-Uncontrolled: Engineering
Artificial intelligence
Computational Intelligence
Soggetto non controllato: Engineering
Artificial intelligence
Computational Intelligence
Termine d'indicizzazione-Occupazione: Engineering
Artificial intelligence
Computational Intelligence
Classificazione LOC: Q325.6 .R45 2012
Creatori/Collaboratori: Wiering, Marco
Otterlo, Martijn van.
Contenuto supplementare: Includes bibliographical references and index.
Nota di contenuto: Part 1. Introductory Part / Reinforcement Learning and Markov Decision Processes / Martijn van Otterlo and Marco Wiering -- Part 2. Efficient Solution Frameworks / Batch Reinforcement Learning / Sascha Lange, Thomas Gabel and Martin Riedmiller -- Least-Squares Methods for Policy Iteration / Lucian Buşoniu, Alessandro Lazaric, Mohammad Ghavamzadeh, Rémi Munos and Robert Babuška, et al. -- Learning and Using Models / Todd Hester and Peter Stone -- Transfer in Reinforcement Learning: A Framework and a Survey / Alessandro Lazaric -- Sample Complexity Bounds of Exploration / Lihong Li -- Part 3. Constructive-Representational Directions / Reinforcement Learning in Continuous State and Action Spaces / Hado van Hasselt -- Solving Relational and First-Order Logical Markov Decision Processes: A Survey / Martijn van Otterlo -- Hierarchical Approaches / Bernhard Hengst -- Evolutionary Computation for Reinforcement Learning / Shimon Whiteson -- Part 4. Probabilistic Models of Self and Others / Bayesian Reinforcement Learning / Nikos Vlassis, Mohammad Ghavamzadeh, Shie Mannor and Pascal Poupart -- Partially Observable Markov Decision Processes / Matthijs T.J. Spaan -- Predictively Defined Representations of State / David Wingate -- Game Theory and Multi-agent Reinforcement Learning / Ann Nowé, Peter Vrancx and Yann-Michaël De Hauwere -- Decentralized POMDPs / Frans A. Oliehoek -- Part 5. Domains and Background / Psychological and Neuroscientific Connections with Reinforcement Learning / Ashvin Shah -- Reinforcement Learning in Games / István Szita -- Reinforcement Learning in Robotics: A Survey / Jens Kober and Jan Peters -- Conclusions, Future Directions and Outlook / Marco Wiering and Martijn van Otterlo.
Restrizioni accesso: Access is restricted to users affiliated with licensed institutions.
Sommario/riassunto: Reinforcement learning encompasses both a science of adaptive behavior of rational beings in uncertain environments and a computational methodology for finding optimal behaviors for challenging problems in control, optimization and adaptive behavior of intelligent agents. As a field, reinforcement learning has progressed tremendously in the past decade. The main goal of this book is to present an up-to-date series of survey articles on the main contemporary sub-fields of reinforcement learning. This includes surveys on partially observable environments, hierarchical task decompositions, relational knowledge representation and predictive state representations. Furthermore, topics such as transfer, evolutionary methods and continuous spaces in reinforcement learning are surveyed. In addition, several chapters review reinforcement learning methods in robotics, in games, and in computational neuroscience. In total seventeen different subfields are presented by mostly young experts in those areas, and together they truly represent a state-of-the-art of current reinforcement learning research. Marco Wiering works at the artificial intelligence department of the University of Groningen in the Netherlands. He has published extensively on various reinforcement learning topics. Martijn van Otterlo works in the cognitive artificial intelligence group at the Radboud University Nijmegen in The Netherlands. He has mainly focused on expressive knowledge representation in reinforcement learning settings.
Collana: Adaptation, learning, and optimization, 1867-4534 ; v. 12
ISBN: 9783642276453
3642276458
364227644X
9783642276446
Formato: Materiale a stampa
Livello bibliografico Monografia
Lingua di pubblicazione: Inglese
Record Nr.: 004374505
Localizzazioni e accesso elettronico http://link.springer.com/10.1007/978-3-642-27645-3
Collocazione: Electronic access
Lo trovi qui: New York University
Altra ed. diverso supporto: Printed edition: 9783642276446