Collaborative multi-agent reinforcement learning based on experience propagation

作     者：Min Fang Frans C.A. Groen 

作者机构：School of Computer Science and Technology Xidian University Informatics Institute University of Amsterdam 

出 版 物：《Journal of Systems Engineering and Electronics》 (系统工程与电子技术（英文版）)

年 卷 期：2013年第24卷第4期

页      面：683-689页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 081104[工学-模式识别与智能系统] 08[工学] 080202[工学-机械电子工程] 0802[工学-机械工程] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China (61070143 61173088) 

主　　题：multi-agent Q learning state list extracting experience sharing. 

摘      要：For multi-agent reinforcement learning in Markov games, knowledge extraction and sharing are key research problems. State list extracting means to calculate the optimal shared state path from state trajectories with cycles. A state list extracting algorithm checks cyclic state lists of a current state in the state trajectory, condensing the optimal action set of the current state. By reinforcing the optimal action selected, the action policy of cyclic states is optimized gradually. The state list extracting is repeatedly learned and used as the experience knowledge which is shared by teams. Agents speed up the rate of convergence by experience sharing. Competition games of preys and predators are used for the experiments. The results of experiments prove that the proposed algorithms overcome the lack of experience in the initial stage, speed up learning and improve the performance.