Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/733
Title: | Reinforcement Learning in Large State Spaces Simulated Robotic Soccer as a Testbed | Authors: | TUYLS, Karl Maes, Sam Manderick, Bernard |
Issue Date: | 2003 | Publisher: | Springer | Source: | ROBOCUP 2002: ROBOT SOCCER WORLD CUP VI. p. 319-326 | Series/Report: | LECTURE NOTES IN ARTIFICIAL INTELLIGENCE | Series/Report no.: | 2752 | Abstract: | Large state spaces and incomplete information are two problems that stand out in learning in multi-agent systems. In this paper we tackle them both by using a combination of decision trees and Bayesian networks (BNs) to model the environment and the Q-function. Simulated robotic soccer is used as a testbed, since there agents are faced with both large state spaces and incomplete information. The long-term goal of this research is to define generic techniques that allow agents to learn in large-scaled multi-agent systems. | Document URI: | http://hdl.handle.net/1942/733 | ISBN: | 3-540-40666-2 | ISSN: | 0302-9743 | DOI: | 10.1007/b11927 | ISI #: | 000185884000027 | Category: | A1 | Type: | Journal Contribution |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Tuylsrl-robo02.pdf | 165.4 kB | Adobe PDF | View/Open |
WEB OF SCIENCETM
Citations
4
checked on Oct 4, 2024
Page view(s)
44
checked on Nov 7, 2023
Download(s)
54
checked on Nov 7, 2023
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.