Adaptive Representations for Reinforcement Learning / Studies in Computational Intelligence Bd.291 (PDF)
(Sprache: Englisch)
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,...
sofort als Download lieferbar
eBook (pdf)
Fr. 118.00
inkl. MwSt.
- Kreditkarte, Paypal, Rechnung
- Kostenloser tolino webreader
Produktdetails
Produktinformationen zu „Adaptive Representations for Reinforcement Learning / Studies in Computational Intelligence Bd.291 (PDF)“
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.
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.
Bibliographische Angaben
- Autor: Shimon Whiteson
- 2010, 2011, 116 Seiten, Englisch
- Verlag: Springer-Verlag GmbH
- ISBN-10: 3642139329
- ISBN-13: 9783642139321
- Erscheinungsdatum: 10.07.2010
Abhängig von Bildschirmgrösse und eingestellter Schriftgrösse kann die Seitenzahl auf Ihrem Lesegerät variieren.
eBook Informationen
- Dateiformat: PDF
- Grösse: 5.27 MB
- Mit Kopierschutz
- Vorlesefunktion
Sprache:
Englisch
Kopierschutz
Dieses eBook können Sie uneingeschränkt auf allen Geräten der tolino Familie lesen. Zum Lesen auf sonstigen eReadern und am PC benötigen Sie eine Adobe ID.
Kommentar zu "Adaptive Representations for Reinforcement Learning / Studies in Computational Intelligence Bd.291"
0 Gebrauchte Artikel zu „Adaptive Representations for Reinforcement Learning / Studies in Computational Intelligence Bd.291“
Zustand | Preis | Porto | Zahlung | Verkäufer | Rating |
---|
Schreiben Sie einen Kommentar zu "Adaptive Representations for Reinforcement Learning / Studies in Computational Intelligence Bd.291".
Kommentar verfassen