Layered learning in multiagent systems : (Record no. 73094)

000 -LEADER
fixed length control field 03724nam a2200517 i 4500
001 - CONTROL NUMBER
control field 6267440
005 - DATE AND TIME OF LATEST TRANSACTION
control field 20220712204706.0
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 151223s2000 maua ob 001 eng d
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
-- print
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
ISBN 9780262284448
-- ebook
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
-- electronic
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
-- electronic
020 ## - INTERNATIONAL STANDARD BOOK NUMBER
-- electronic
100 1# - AUTHOR NAME
Author Stone, Peter,
245 10 - TITLE STATEMENT
Title Layered learning in multiagent systems :
Sub Title a winning approach to robotic soccer /
300 ## - PHYSICAL DESCRIPTION
Number of Pages 1 PDF (xii, 272 pages) :
490 1# - SERIES STATEMENT
Series statement Intelligent robotics and autonomous agents series
505 0# - FORMATTED CONTENTS NOTE
Remark 2 Introduction -- Substrate systems -- Team member agent architecture -- Layered learning -- Learning an individual skill -- Learning a multiagent behavior -- Learning a team behavior -- Competition results -- Related work -- Conclusions and future work.
520 ## - SUMMARY, ETC.
Summary, etc 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.
856 42 - ELECTRONIC LOCATION AND ACCESS
Uniform Resource Identifier https://ieeexplore.ieee.org/xpl/bkabstractplus.jsp?bkn=6267440
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Koha item type eBooks
264 #1 -
-- Cambridge, Massachusetts :
-- MIT Press,
-- c2000.
264 #2 -
-- [Piscataqay, New Jersey] :
-- IEEE Xplore,
-- [2000]
336 ## -
-- text
-- rdacontent
337 ## -
-- electronic
-- isbdmedia
338 ## -
-- online resource
-- rdacarrier
588 ## -
-- Description based on PDF viewed 12/23/2015.
650 #0 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Robotics.
650 #0 - SUBJECT ADDED ENTRY--SUBJECT 1
-- Multiagent systems.

No items available.