Multi-agent Reinforcement Learning Based on K-Means Algorithm  

作　　者：LIU Changan LIU Fei LIU Chunyang WU Hua 

机构地区：[1]School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China

出　　处：《Chinese Journal of Electronics》2011年第3期414-418,共5页电子学报（英文版）

基　　金：This work is supported by the National Natural Science Foundation of China （No.60775058）, the Fundamental Research Funds for the Central Universities （No.10ZG07）.

摘　　要：To solve the curse of dimensionality and structure credit assignment in multi-agent reinforcement learning, a learning method based on K-Means is proposed in this paper. With this method, state space explosion is avoided by classifying states into different clusters using K-Means. The roles are dynamic assigned to agents and the corresponding set of characteristic behaviours is estab- lished by using K-Means algorithm. The credit assignment function is designed according to factors like the weight of roles. The experimental results of the multi-robot cooperation show that our scheme improves the team learning ability efficiently. Meanwhile, the cooperation efficiency can be enhanced successfully.

关 键 词：Multi-agent systems Reinforcementlearning K-MEANS Role-clustering Credit assignment. 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TP18[自动化与计算机技术—计算机科学与技术]