Skip to main content
SpringerLink
Log in
Book cover

Reinforcement Learning

  • Book
  • © 1992

Overview

Editors:
  1. Richard S. Sutton

    1. GTE Laboratories, USA

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

Part of the book series: The Springer International Series in Engineering and Computer Science (SECS, volume 173)

This is a preview of subscription content, log in via an institution to check access.

Access this book

Log in via an institution
eBook USD 169.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book USD 219.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

Licence this eBook for your library

Institutional subscriptions

Table of contents (8 chapters)

  1. Front Matter

    Pages iii-vi
    Download chapter PDF

  2. Introduction: The Challenge of Reinforcement Learning

    • Richard S. Sutton
    Pages 1-3

  3. Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

    • Ronald J. Williams
    Pages 5-32

  4. Practical Issues in Temporal Difference Learning

    • Gerald Tesauro
    Pages 33-53

  5. Technical Note

    • Christopher J. C. H. Watkins, Peter Dayan
    Pages 55-68

  6. Self-Improving Reactive Agents Based on Reinforcement Learning, Planning and Teaching

    • Long-Ji Lin
    Pages 69-97

  7. Transfer of Learning by Composing Solutions of Elemental Sequential Tasks

    • Satinder Pal Singh
    Pages 99-115

  8. The Convergence of TD(λ) for General λ

    • Peter Dayan
    Pages 117-138

  9. A Reinforcement Connectionist Approach to Robot Path Finding in Non-Maze-Like Environments

    • José R. Del Millán, Carme Torras
    Pages 139-171

  10. Back Matter

    Pages 172-172
    Download chapter PDF
Back to top

Keywords

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.

Editors and Affiliations

  • GTE Laboratories, USA

    Richard S. Sutton

Bibliographic Information

Publish with us

Policies and ethics

Back to top

Search

Navigation