The Springer International Series in Engineering and Computer Science

Reinforcement Learning

Editors: Sutton, Richard S. (Ed.)

Buy this book

eBook $229.00 net
( price for USA )
  • ISBN 978-1-4615-3618-5
  • digitally watermarked, no DRM
  • included format: PDF
  • eBooks can be used on all Reading Devices
Hardcover $289.00 net
( price for USA )
  • ISBN 978-0-7923-9234-7
  • free shipping for individuals worldwide
  • usually dispatched within 3 to 5 business days
Softcover $289.00 net
( price for USA )
  • ISBN 978-1-4613-6608-9
  • free shipping for individuals worldwide
  • usually dispatched within 3 to 5 business days
About this book

Reinforcement learning is the learning of a mapping from situations to actions so as to maximize a scalar reward or reinforcement signal. The learner is not told which action to take, as in most forms of machine learning, but instead must discover which actions yield the highest reward by trying them. In the most interesting and challenging cases, actions may affect not only the immediate reward, but also the next situation, and through that all subsequent rewards. These two characteristics -- trial-and-error search and delayed reward -- are the most important distinguishing features of reinforcement learning.
Reinforcement learning is both a new and a very old topic in AI. The term appears to have been coined by Minsk (1961), and independently in control theory by Walz and Fu (1965). The earliest machine learning research now viewed as directly relevant was Samuel's (1959) checker player, which used temporal-difference learning to manage delayed reward much as it is used today. Of course learning and reinforcement have been studied in psychology for almost a century, and that work has had a very strong impact on the AI/engineering work. One could in fact consider all of reinforcement learning to be simply the reverse engineering of certain psychological learning processes (e.g. operant conditioning and secondary reinforcement).
Reinforcement Learning is an edited volume of original research, comprising seven invited contributions by leading researchers.

Table of contents (3 chapter)

  • Introduction: The Challenge of Reinforcement Learning

    Richard S. Sutton

    Pages 1-3

    Buy Chapter $29.95
  • Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

    Ronald J. Williams

    Pages 5-32

    Buy Chapter $29.95
  • Practical Issues in Temporal Difference Learning

    Gerald Tesauro

    Pages 33-53

    Buy Chapter $29.95
Free Preview

Buy this book

eBook $229.00 net
( price for USA )
  • ISBN 978-1-4615-3618-5
  • digitally watermarked, no DRM
  • included format: PDF
  • eBooks can be used on all Reading Devices
Hardcover $289.00 net
( price for USA )
  • ISBN 978-0-7923-9234-7
  • free shipping for individuals worldwide
  • usually dispatched within 3 to 5 business days
Softcover $289.00 net
( price for USA )
  • ISBN 978-1-4613-6608-9
  • free shipping for individuals worldwide
  • usually dispatched within 3 to 5 business days

Recommended for you

Loading...

Bibliographic Information

Bibliographic Information
Book Title
Reinforcement Learning
Series Title
The Springer International Series in Engineering and Computer Science
Series Volume
173
Copyright
1992
Publisher
Springer US
Copyright Holder
Springer Science+Business Media New York
eBook ISBN
978-1-4615-3618-5
DOI
10.1007/978-1-4615-3618-5
Hardcover ISBN
978-0-7923-9234-7
Softcover ISBN
978-1-4613-6608-9
Series ISSN
0893-3405
Edition Number
1
Topics