Verwandte Artikel zu Adaptive Representations for Reinforcement Learning...
Adaptive Representations for Reinforcement Learning (Studies in Computational Intelligence, 291, Band 291) - Hardcover
Inhaltsangabe
This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own representations have the potential to dramatically improve performance. This book introduces two novel approaches for automatically discovering high-performing representations. The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for a broad class of optimization problems. This synthesis is accomplished by customizing evolutionary methods to the on-line nature of reinforcement learning and using them to evolve representations for value function approximators. The second approach automatically learns representations based on piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements. This book also introduces a novel method for devising input representations. This method addresses the feature selection problem by extending an algorithm that evolves the topology and weights of neural networks such that it evolves their inputs too. In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially improve performance over methods with manual representations.
Die Inhaltsangabe kann sich auf eine andere Ausgabe dieses Titels beziehen.
Über die Autorin bzw. den Autor
Diederik M. Roijers completed his master's in Computing Science at Utrecht University before obtaining his Ph.D. in Artificial Intelligence under the supervision of Shimon Whiteson and Frans A. Oliehoek at the University of Amsterdam in 2016. He then joined the University of Oxford as a postdoctoral research assistant. He was awarded a Postdoctoral Fellowship Grant from the FWO (Research Foundation - Flanders) and started as an FWO Postdoctoral Fellow at the Vrije Universiteit Brussel in October 2016. His research focuses on creating intelligent autonomous systems that assist humans in solving complex problems, especially those with multiple objectives. To this end, he focuses ondecision-theoretic planning and learning, which enable agents to use mathematical models to reason about the environments in which they operate. In the multi-objective problems he has been studying, the agents produce a set of possibly optimal policies that offer different trade-offs with respect to the objectives, to help users make an informed decision.
Shimon Whiteson studied English and Computer Science at Rice University before completing his doctorate in Computer Science under the supervision of Peter Stone at the University of Texas at Austin in 2007. He then spent eight years as an Assistant and then an Associate Professor at the University of Amsterdam before joining the University of Oxford as an Associate Professor in 2015. He was awarded an ERC Starting Grant from the European Research Council in 2014. His research focuses on artificial intelligence with the goal of designing, analyzing, and evaluating the algorithms that enable computational systems to acquire and execute intelligent behavior. He is particularly interested in machine learning, with which computers can learn from experience, and decision-theoretic planning, with which they can reason about their goals and deduce behavioral strategies that maximize their utility. In addition to theoretical work on these topics, he has in recent years also focused on applying them to practical problems in robotics and search engine optimization.
Von der hinteren Coverseite
This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own representations have the potential to dramatically improve performance. This book introduces two novel approaches for automatically discovering high-performing representations. The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for a broad class of optimization problems. This synthesis is accomplished by customizing evolutionary methods to the on-line nature of reinforcement learning and using them to evolve representations for value function approximators. The second approach automatically learns representations based on piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements. This book also introduces a novel method for devising input representations. This method addresses the feature selection problem by extending an algorithm that evolves the topology and weights of neural networks such that it evolves their inputs too. In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially improve performance over methods with manual representations.
„Über diesen Titel“ kann sich auf eine andere Ausgabe dieses Titels beziehen.
Suchergebnisse für Adaptive Representations for Reinforcement Learning...
Beispielbild für diese ISBN
Adaptive Representations for Reinforcement Learning (eng)
Print-on-DemandAnbieter: Brook Bookstore On Demand, Napoli, NA, Italien
Verkäuferbewertung 5 von 5 Sternen
Zustand: new. Questo è un articolo print on demand. Bestandsnummer des Verkäufers d81d4855b92c9a10a96232493e9ca9e5
Neu kaufen
EUR 86,24
EUR 5,50 Versand
Versand von Italien nach USA
Versand von Italien nach USA
Anzahl: Mehr als 20 verfügbar
Foto des Verkäufers
Adaptive Representations for Reinforcement Learning
Verlag:
Springer Berlin Heidelberg Okt 2010, 2010
ISBN 10: 3642139310
ISBN 13: 9783642139314
Neu
Hardcover
Anbieter: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Deutschland
Verkäuferbewertung 5 von 5 Sternen
Buch. Zustand: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own representations have the potential to dramatically improve performance. This book introduces two novel approaches for automatically discovering high-performing representations.The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for a broad class ofoptimization problems. This synthesis is accomplished by customizing evolutionarymethods to the on-line nature of reinforcement learning and using them to evolve representations for value function approximators.The second approach automatically learns representations based on piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements.This book also introduces a novel method for devising input representations. This method addresses the feature selection problem by extending an algorithm that evolves the topology and weights of neural networks such that it evolves their inputs too.In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially improve performance over methodswith manual representations. 132 pp. Englisch. Bestandsnummer des Verkäufers 9783642139314
Neu kaufen
EUR 106,99
EUR 23,00 Versand
Versand von Deutschland nach USA
Versand von Deutschland nach USA
Anzahl: 2 verfügbar
Beispielbild für diese ISBN
Adaptive Representations for Reinforcement Learning (Studies in Computational Intelligence, 291)
Anbieter: California Books, Miami, FL, USA
Verkäuferbewertung 5 von 5 Sternen
Zustand: New. Bestandsnummer des Verkäufers I-9783642139314
Neu kaufen
EUR 130,15
EUR 2,69 Versand
Versand innerhalb von USA
Versand innerhalb von USA
Anzahl: Mehr als 20 verfügbar
Beispielbild für diese ISBN
Adaptive Representations for Reinforcement Learning
Anbieter: GreatBookPrices, Columbia, MD, USA
Verkäuferbewertung 5 von 5 Sternen
Zustand: New. Bestandsnummer des Verkäufers 10255197-n
Neu kaufen
EUR 130,47
EUR 2,37 Versand
Versand innerhalb von USA
Versand innerhalb von USA
Anzahl: 15 verfügbar
Foto des Verkäufers
Adaptive Representations for Reinforcement Learning
Print-on-DemandAnbieter: moluna, Greven, Deutschland
Verkäuferbewertung 5 von 5 Sternen
Gebunden. Zustand: New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Recent research in Adaptive Representations for Reinforcement LearningWritten by leading experts in this fieldState-of-the Art bookThis book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seek. Bestandsnummer des Verkäufers 5050346
Neu kaufen
EUR 92,27
EUR 48,99 Versand
Versand von Deutschland nach USA
Versand von Deutschland nach USA
Anzahl: Mehr als 20 verfügbar
Foto des Verkäufers
Adaptive Representations for Reinforcement Learning
ISBN 10: 3642139310
ISBN 13: 9783642139314
Neu
Hardcover
Anbieter: Rarewaves.com USA, London, LONDO, Vereinigtes Königreich
Verkäuferbewertung 5 von 5 Sternen
Hardback. Zustand: New. 2011th. This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own representations have the potential to dramatically improve performance. This book introduces two novel approaches for automatically discovering high-performing representations. The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for a broad class ofoptimization problems. This synthesis is accomplished by customizing evolutionarymethods to the on-line nature of reinforcement learning and using them to evolve representations for value function approximators.The second approach automatically learns representations based on piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements. This book also introduces a novel method for devising input representations. This method addresses the feature selection problem by extending an algorithm that evolves the topology and weights of neural networks such that it evolves their inputs too.In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially improve performance over methodswith manual representations. Bestandsnummer des Verkäufers LU-9783642139314
Neu kaufen
EUR 148,00
Versand gratis
Versand von Vereinigtes Königreich nach USA
Versand von Vereinigtes Königreich nach USA
Anzahl: Mehr als 20 verfügbar
Foto des Verkäufers
Adaptive Representations for Reinforcement Learning
Anbieter: AHA-BUCH GmbH, Einbeck, Deutschland
Verkäuferbewertung 5 von 5 Sternen
Buch. Zustand: Neu. Druck auf Anfrage Neuware - Printed after ordering - This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own representations have the potential to dramatically improve performance. This book introduces two novel approaches for automatically discovering high-performing representations.The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for a broad class ofoptimization problems. This synthesis is accomplished by customizing evolutionarymethods to the on-line nature of reinforcement learning and using them to evolve representations for value function approximators.The second approach automatically learns representations based on piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements.This book also introduces a novel method for devising input representations. This method addresses the feature selection problem by extending an algorithm that evolves the topology and weights of neural networks such that it evolves their inputs too.In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially improve performance over methodswith manual representations. Bestandsnummer des Verkäufers 9783642139314
Neu kaufen
EUR 124,85
EUR 35,00 Versand
Versand von Deutschland nach USA
Versand von Deutschland nach USA
Anzahl: 1 verfügbar
Foto des Verkäufers
Adaptive Representations for Reinforcement Learning
Print-on-DemandAnbieter: buchversandmimpf2000, Emtmannsberg, BAYE, Deutschland
Verkäuferbewertung 5 von 5 Sternen
Buch. Zustand: Neu. This item is printed on demand - Print on Demand Titel. Neuware -This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own representations have the potential to dramatically improve performance. This book introduces two novel approaches for automatically discovering high-performing representations.The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for a broad class ofoptimization problems. This synthesis is accomplished by customizing evolutionarymethods to the on-line nature of reinforcement learning and using them to evolve representations for value function approximators.The second approach automatically learns representations based on piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements.This book also introduces a novel method for devising input representations. This method addresses the feature selection problem by extending an algorithm that evolves the topology and weights of neural networks such that it evolves their inputs too.In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially improve performance over methodswith manual representations.Springer-Verlag KG, Sachsenplatz 4-6, 1201 Wien 132 pp. Englisch. Bestandsnummer des Verkäufers 9783642139314
Neu kaufen
EUR 106,99
EUR 60,00 Versand
Versand von Deutschland nach USA
Versand von Deutschland nach USA
Anzahl: 1 verfügbar
Beispielbild für diese ISBN
Adaptive Representations for Reinforcement Learning
Anbieter: Revaluation Books, Exeter, Vereinigtes Königreich
Verkäuferbewertung 5 von 5 Sternen
Hardcover. Zustand: Brand New. 133 pages. 9.00x6.25x0.25 inches. In Stock. Bestandsnummer des Verkäufers x-3642139310
Neu kaufen
EUR 157,83
EUR 12,00 Versand
Versand von Vereinigtes Königreich nach USA
Versand von Vereinigtes Königreich nach USA
Anzahl: 2 verfügbar
Beispielbild für diese ISBN
Adaptive Representations for Reinforcement Learning
Anbieter: Buchpark, Trebbin, Deutschland
Verkäuferbewertung 5 von 5 Sternen
Zustand: Sehr gut. Zustand: Sehr gut | Sprache: Englisch | Produktart: Bücher | This book presents new algorithms for reinforcement learning, a form of machine learning in which an autonomous agent seeks a control policy for a sequential decision task. Since current methods typically rely on manually designed solution representations, agents that automatically adapt their own representations have the potential to dramatically improve performance. This book introduces two novel approaches for automatically discovering high-performing representations. The first approach synthesizes temporal difference methods, the traditional approach to reinforcement learning, with evolutionary methods, which can learn representations for a broad class ofoptimization problems. This synthesis is accomplished by customizing evolutionarymethods to the on-line nature of reinforcement learning and using them to evolve representations for value function approximators.The second approach automatically learns representations based on piecewise-constant approximations of value functions. It begins with coarse representations and gradually refines them during learning, analyzing the current policy and value function to deduce the best refinements. This book also introduces a novel method for devising input representations. This method addresses the feature selection problem by extending an algorithm that evolves the topology and weights of neural networks such that it evolves their inputs too.In addition to introducing these new methods, this book presents extensive empirical results in multiple domains demonstrating that these techniques can substantially improve performance over methodswith manual representations. Bestandsnummer des Verkäufers 7906270/2
Gebraucht kaufen
EUR 77,24
EUR 105,00 Versand
Versand von Deutschland nach USA
Versand von Deutschland nach USA
Anzahl: 1 verfügbar