In this Book

The MIT Press
summary

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.

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.

Table of Contents

  1. Cover
  2. open access View |
  1. Title Page
  2. open access View |
  1. Copyright
  2. open access View |
  1. Dedication
  2. pp. v-vi
  3. open access View |
  1. Contents
  2. pp. vii-xii
  3. open access View |
  1. Foreword
  2. pp. xiii-xiv
  3. open access View |
  1. Preface
  2. pp. xv-xviii
  3. open access View |
  1. I. The Problem
  2. pp. 1-2
  3. open access View |
  1. 1. Introduction
  2. pp. 3-24
  3. open access View |
  1. 2. Evaluative Feedback
  2. pp. 25-50
  3. open access View |
  1. 3. The Reinforcement Learning Problem
  2. pp. 51-86
  3. open access View |
  1. II. Elementary Solution Methods
  2. pp. 87-88
  3. open access View |
  1. 4. Dynamic Programming
  2. pp. 89-110
  3. open access View |
  1. 5. Monte Carlo Methods
  2. pp. 111-132
  3. open access View |
  1. 6. Temporal-Difference Learning 133
  2. pp. 133-160
  3. open access View |
  1. III. A Unified View
  2. pp. 161-162
  3. open access View |
  1. 7. Eligibility Traces
  2. pp. 163-192
  3. open access View |
  1. 8. Generalization and Function Approximation
  2. pp. 193-226
  3. open access View |
  1. 9. Planning and Learning
  2. pp. 227-254
  3. open access View |
  1. 10. Dimensions of Reinforcement Learning
  2. pp. 255-260
  3. open access View |
  1. 11. Case Studies
  2. pp. 261-290
  3. open access View |
  1. References
  2. pp. 291-312
  3. open access View |
  1. Summary of Notation
  2. pp. 313-314
  3. open access View |
  1. Index
  2. pp. 315-322
  3. open access View |

Additional Information

ISBN
9780262257053
Related ISBN
9780262193986
MARC Record
OCLC
1053169863
Launched on MUSE
2018-09-19
Open Access
Yes
Back To Top

This website uses cookies to ensure you get the best experience on our website. Without cookies your experience may not be seamless.