Reinforcement Learning: An Introduction

Front Cover
MIT Press, 1998 - Computers - 322 pages
10 Reviews

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.

 

What people are saying - Write a review

User ratings

5 stars
6
4 stars
4
3 stars
0
2 stars
0
1 star
0

User Review - Flag as inappropriate

http://books.google.com/books?id=CAFR6IBF4xYC&printsec=frontcover

Contents

Introduction
3
Evaluative Feedback
25
Elementary Solution Methods
87
A Unified View
161
Generalization and Function Approximation
193
Planning and Learning
227
Dimensions of Reinforcement Learning
255
Case Studies
261
References
291
Summary of Notation
313
Copyright

Other editions - View all

Common terms and phrases

Popular passages

Page 301 - Proceedings of the Second International Conference on Simulation of Adaptive Behavior: From Animals to Animals, 2, 460-468.

References to this book

All Book Search results »

About the author (1998)

Richard S. Sutton is Senior Research Scientist, Department of Computer Science, University of Massachusetts.