Reinforcement Learning: An Introduction

Reinforcement Learning: An Introduction

Provides a clear and simple account of the key ideas and algorithms of reinforcement learning. Familiarity with elementary concepts of probability is assumed.

Publication date: 01 Mar 1998

ISBN-10: 0262193981

ISBN-13: 9780262193986

Paperback: 322 pages

Views: 15,771

Publisher: The MIT Press

License: n/a

Post time: 05 Oct 2007 12:23:36

Reinforcement Learning: An Introduction

Reinforcement Learning: An Introduction Provides a clear and simple account of the key ideas and algorithms of reinforcement learning. Familiarity with elementary concepts of probability is assumed.
Tag(s): Artificial Intelligence Neural Networks Operations Research
Publication date: 01 Mar 1998
ISBN-10: 0262193981
ISBN-13: 9780262193986
Paperback: 322 pages
Views: 15,771
Publisher: The MIT Press
License: n/a
Post time: 05 Oct 2007 12:23:36
Book Description:

Reinforcement learning, one of the most active research areas in artificial intelligence, is a computational approach to learning whereby an agent tries to maximize the total amount of reward it receives when interacting with a complex, uncertain environment. In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning. Their discussion ranges from the history of the field's intellectual foundations to the most recent developments and applications. The only necessary mathematical background is familiarity with elementary concepts of probability.

The book is divided into three parts. Part I defines the reinforcement learning problem in terms of Markov decision processes. Part II provides basic solution methods: dynamic programming, Monte Carlo methods, and temporal-difference learning. Part III presents a unified view of the solution methods and incorporates artificial neural networks, eligibility traces, and planning; the two final chapters present case studies and consider the future of reinforcement learning.

Reviews:

Amazon.com

:) "The book is very readable by average computer students. Possibly the only difficult one is chapter 8, which deals with some neural network concepts. I highly recommend this book to anyone who wants to learn about this subject. "

:) "The book is easy and interesting to read. The diagrams, especially those on TD, throw a great deal of insight on the basic concept of TD. The intuitive ideas behind RL are developed clearly. At the same time all the fundamental concepts are made mathematically precise using very simple language and notation. Anybody new to RL should find this book extremely useful."




About The Author(s)


Andrew Barto is Professor Emeritus in the College of Information and Computer Sciences at University of Massachusetts Amherst. He is a Co-Director at Autonomous Learning Laboratory. His research interests are theory and application of methods for learning and planning in stochastic sequential decision problems; algebraic approaches to abstraction; psychology, neuroscience, and computational theory of motivation, reward, and addiction; computational models of learning and adaptation in animal motor control systems. 

Andrew G. Barto

Andrew Barto is Professor Emeritus in the College of Information and Computer Sciences at University of Massachusetts Amherst. He is a Co-Director at Autonomous Learning Laboratory. His research interests are theory and application of methods for learning and planning in stochastic sequential decision problems; algebraic approaches to abstraction; psychology, neuroscience, and computational theory of motivation, reward, and addiction; computational models of learning and adaptation in animal motor control systems. 


Richard S. Sutton is Professor and iCORE chair Department of Computing Science at University of Alberta. Dr. Sutton is considered one of the founding fathers of modern computational reinforcement learning, having several significant contributions to the field, including temporal difference learning, policy gradient methods, the Dyna architecture.

Richard S. Sutton

Richard S. Sutton is Professor and iCORE chair Department of Computing Science at University of Alberta. Dr. Sutton is considered one of the founding fathers of modern computational reinforcement learning, having several significant contributions to the field, including temporal difference learning, policy gradient methods, the Dyna architecture.



Book Categories