Multi-agent coordination method based on Markov game and application to robot soccer

Bo Fan, Quan Pan, Hong Cai Zhang

科研成果: 期刊稿件文章同行评审

3 引用 (Scopus)

摘要

A layered multi-agent coordination method based on Markov games is presented. According to the relationship of competition and cooperation among the multiple agents, this method adopts the zero-sum Markov game in high layer to compete with the opponent and adopts the team Markov game in low layer to accomplish cooperation in the team. With the application and experiment in Robot Soccer, it is shown that this method is better than the traditional multi-agent learning method.

源语言英语
页(从-至)46-51
页数6
期刊Jiqiren/Robot
27
1
出版状态已出版 - 1月 2005

指纹

探究 'Multi-agent coordination method based on Markov game and application to robot soccer' 的科研主题。它们共同构成独一无二的指纹。

引用此