Advertisement

TEXPLORE: Temporal Difference Reinforcement Learning for Robots and Time-Constrained Domains

  • Todd Hester

Part of the Studies in Computational Intelligence book series (SCI, volume 503)

Table of contents

  1. Front Matter
    Pages 1-11
  2. Todd Hester
    Pages 1-9
  3. Todd Hester
    Pages 11-23
  4. Todd Hester
    Pages 25-34
  5. Todd Hester
    Pages 35-49
  6. Todd Hester
    Pages 51-84
  7. Todd Hester
    Pages 85-119
  8. Todd Hester
    Pages 121-135
  9. Todd Hester
    Pages 137-147
  10. Back Matter
    Pages 149-164

About this book

Introduction

This book presents and develops new reinforcement learning methods that enable fast and robust learning on robots in real-time.

Robots have the potential to solve many problems in society, because of their ability to work in dangerous places doing necessary jobs that no one wants or is able to do. One barrier to their widespread deployment is that they are mainly limited to tasks where it is possible to hand-program behaviors for every situation that may be encountered. For robots to meet their potential, they need methods that enable them to learn and adapt to novel situations that they were not programmed for. Reinforcement learning (RL) is a paradigm for learning sequential decision making processes and could solve the problems of learning and adaptation on robots. This book identifies four key challenges that must be addressed for an RL algorithm to be practical for robotic control tasks. These RL for Robotics Challenges are: 1) it must learn in very few samples; 2) it must learn in domains with continuous state features; 3) it must handle sensor and/or actuator delays; and 4) it should continually select actions in real time. This book focuses on addressing all four of these challenges. In particular, this book is focused on time-constrained domains where the first challenge is critically important. In these domains, the agent’s lifetime is not long enough for it to explore the domains thoroughly, and it must learn in very few samples.

Keywords

Computational Intelligence Model Based RL Real-Time Sample Efficient Reinforcement Learning Reinforcement Learning Reinforcement Learning for Robots TEXPLORE Temporal Difference Reinforcement Learning for Robots

Authors and affiliations

  • Todd Hester
    • 1
  1. 1., Department of Computer ScienceUniversity of Texas at AustinAustinUSA

Bibliographic information

  • DOI https://doi.org/10.1007/978-3-319-01168-4
  • Copyright Information Springer International Publishing Switzerland 2013
  • Publisher Name Springer, Heidelberg
  • eBook Packages Engineering
  • Print ISBN 978-3-319-01167-7
  • Online ISBN 978-3-319-01168-4
  • Series Print ISSN 1860-949X
  • Series Online ISSN 1860-9503
  • Buy this book on publisher's site