9780262194389

Layered Learning in Multiagent Systems : A Winning Approach to Robotic Soccer

by
  • ISBN13:

    9780262194389

  • ISBN10:

    0262194384

  • Format: Hardcover
  • Copyright: 2000-03-17
  • Publisher: Bradford Books
  • Purchase Benefits
  • Free Shipping On Orders Over $35!
    Your order must be $35 or more to qualify for free economy shipping. Bulk sales, PO's, Marketplace items, eBooks and apparel do not qualify for this offer.
  • Get Rewarded for Ordering Your Textbooks! Enroll Now
List Price: $11.75 Save up to $0.35
  • Buy New
    $11.40

    SPECIAL ORDER: 1-2 WEEKS

Supplemental Materials

What is included with this book?

  • The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

Summary

This book looks at multiagent systems that consist of teams of autonomous agents acting in real-time, noisy, collaborative, and adversarial environments. The book makes four main contributions to the fields of machine learning and multiagent systems. First, it describes an architecture within which a flexible team structure allows member agents to decompose a task into flexible roles and to switch roles while acting. Second, it presents layered learning, a general-purpose machine-learning method for complex domains in which learning a mapping directly from agents' sensors to their actuators is intractable with existing machine-learning methods. Third, the book introduces a new multiagent reinforcement learning algorithm--team-partitioned, opaque-transition reinforcement learning (TPOT-RL)--designed for domains in which agents cannot necessarily observe the state-changes caused by other agents' actions. The final contribution is a fully functioning multiagent system that incorporates learning in a real-time, noisy domain with teammates and adversaries--a computer-simulated robotic soccer team. Peter Stone's work is the basis for the CMUnited Robotic Soccer Team, which has dominated recent RoboCup competitions. RoboCup not only helps roboticists to prove their theories in a realistic situation, but has drawn considerable public and professional attention to the field of intelligent robotics. The CMUnited team won the 1999 Stockholm simulator competition, outscoring its opponents by the rather impressive cumulative score of 110-0.

Table of Contents

Preface ix
Introduction
1(8)
Substrate Systems
9(32)
Team Member Agent Architecture
41(48)
Layered Learning
89(16)
Learning an Individual Skill
105(12)
Learning a Multiagent Behavior
117(24)
Learning a Team Behavior
141(40)
Competition Results
181(16)
Related Work
197(34)
Conclusions and Future Work
231(8)
Appendix A: List of Acronyms 239(2)
Appendix B: Robotic Soccer Agent Skills 241(14)
Appendix C: CMUnited-98 Simulator Team Behavior Modes 255(4)
Appendix D: CMUnited Simulator Team Source Code 259(2)
References 261

Rewards Program

Write a Review