A multi-agent coordination framework based on Markov games

Bo Fan, Quan Pan, H. Cai Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Scopus citations

Abstract

Based on the analysis of the reinforcement learning and Markov games, the paper proposes a layered multi-agent coordination framework Based on the multi-agent's interaction of competition and cooperation, this coordination framework adopts the zero-sum Markov game in higher layer to compete with opponent and adopts the team Markov game in lower layer to accomplish the team's cooperation. This coordination framework is applied to Robot Soccer. The results of the experiment illuminate that our proposed method is better than the traditional multi-agent learning.

Original languageEnglish
Title of host publicationCSCWD 2004 - 8th International Conference on Computer Supported Cooperative Work in Design - Proceedings
EditorsW. Shen, T. Li, Z. Lin, J.-P. Bartes, W. Zeng, S. Li, C. Yang
Pages230-233
Number of pages4
StatePublished - 2004
EventCSCWD 2004 - 8th International Conference on Computer Supported Cooperative Work in Design - Proceedings - Xiamen, China
Duration: 26 May 200428 May 2004

Publication series

NameCSCWD 2004 - 8th International Conference on Computer Supported Cooperative Work in Design - Proceedings
Volume2

Conference

ConferenceCSCWD 2004 - 8th International Conference on Computer Supported Cooperative Work in Design - Proceedings
Country/TerritoryChina
CityXiamen
Period26/05/0428/05/04

Fingerprint

Dive into the research topics of 'A multi-agent coordination framework based on Markov games'. Together they form a unique fingerprint.

Cite this