Transfer in Reinforcement Learning Domains

  • Matthew E. Taylor

Part of the Studies in Computational Intelligence book series (SCI, volume 216)

Table of contents

  1. Front Matter
  2. Matthew E. Taylor
    Pages 1-13
  3. Matthew E. Taylor
    Pages 15-29
  4. Matthew E. Taylor
    Pages 31-60
  5. Matthew E. Taylor
    Pages 61-90
  6. Matthew E. Taylor
    Pages 91-120
  7. Matthew E. Taylor
    Pages 121-138
  8. Matthew E. Taylor
    Pages 181-204
  9. Matthew E. Taylor
    Pages 205-218
  10. Back Matter

About this book

Introduction

In reinforcement learning (RL) problems, learning agents sequentially execute actions with the goal of maximizing a reward signal. The RL framework has gained popularity with the development of algorithms capable of mastering increasingly complex problems, but learning difficult tasks is often slow or infeasible when RL agents begin with no prior knowledge. The key insight behind "transfer learning" is that generalization may occur not only within tasks, but also across tasks. While transfer has been studied in the psychological literature for many years, the RL community has only recently begun to investigate the benefits of transferring knowledge. This book provides an introduction to the RL transfer problem and discusses methods which demonstrate the promise of this exciting area of research.

The key contributions of this book are:

    • Definition of the transfer problem in RL domains
    • Background on RL, sufficient to allow a wide audience to understand discussed transfer concepts
    • Taxonomy for transfer methods in RL
    • Survey of existing approaches
    • In-depth presentation of selected transfer methods
    • Discussion of key open questions

By way of the research presented in this book, the author has established himself as the pre-eminent worldwide expert on transfer learning in sequential decision making tasks. A particular strength of the research is its very thorough and methodical empirical evaluation, which Matthew presents, motivates, and analyzes clearly in prose throughout the book. Whether this is your initial introduction to the concept of transfer learning, or whether you are a practitioner in the field looking for nuanced details, I trust that you will find this book to be an enjoyable and enlightening read.

Peter Stone, Associate Professor of Computer Science

Keywords

Computational Intelligence Data Mining Distributed Environments Information Retrieval Signal agents algorithm algorithms computer science development knowledge learning reinforcement learning

Authors and affiliations

  • Matthew E. Taylor
    • 1
  1. 1.Postdoctoral Research Associate, Department of Computer ScienceThe University of Southern CaliforniaLos AngelesUSA

Bibliographic information

  • DOI https://doi.org/10.1007/978-3-642-01882-4
  • Copyright Information Springer Berlin Heidelberg 2009
  • Publisher Name Springer, Berlin, Heidelberg
  • eBook Packages Engineering
  • Print ISBN 978-3-642-01881-7
  • Online ISBN 978-3-642-01882-4
  • Series Print ISSN 1860-949X
  • Series Online ISSN 1860-9503
  • About this book