A NewMulti-agent Reinforcement Learning Approach

摘要：

A new multi-agent reinforcement learning approach is proposed to learn the optimal behaviors among cooperative agent teams. The approach combines advantages of the integer programming, single agent learning and repeated game in a multi-agent framework. The integer programming is used to build cooperative teams in order to prevent the curse of dimensionality. Every cooperative team learns independently, whose members take the best response actions in the light of other agents actions in the same condition, after many repeated games, the aim root could be found. Because of other agents influence, the process of learning is supervised periodically, then through changing the learning rate to gain the right learning results. Simulation results on pursuit problem show that the proposed learning approach overcomes the divergence and improves learning speed obviously.

关键词： multi-agent system(MAS) reinforcement learning Q-learning pursuit problem

作者: Jun Li Qishu Pan Bingrong Hong

作者单位: School of Computer Science and Technology Harbin Institute of Technology Harbin,Heilongjiang Province 150008,China

会议类型: 国际会议

会议名称: 2010 IEEE信息与自动化国际会议(ICIA 2010)

会议地点: 哈尔滨

会议语种:英文

页码: 1-5

在线出版日期: 2010-06-20（万方平台首次上网日期，不代表论文的发表时间）