范波, 潘泉, 张洪才. 基于Markov对策的多智能体协调方法及其在Robot Soccer中的应用[J]. 机器人, 2005, 27(1): 46-51..
FAN Bo, PAN Quan, ZHANG Hong-cai. A Multi-agent Coordination Method Based on Markov Game and Application to Robot Soccer. ROBOT, 2005, 27(1): 46-51..
Abstract：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.
[1] 杨煜普,李晓萌,许晓鸣.多智能体协作技术综述[J].信息与控制,2001,30(4):337-342. [2] Littman M L. Markov games as a framework for multi-agent reinforcement learning [A]. Proceedings of the Eleventh International Conference on Machine Learning[C]. 1994,11:157-163. [3] Owen G. Game Theory (2nd Edition) [M]. Orlando, FL, USA:Academic Press, 1982. [4] Littman M L. Value-function reinforcement learning in Markov games [J]. Journal of Cognitive Systems Research, 2001,1 (12):1-12. [5] Hu J, Wellman M P. Multiagent reinforcement learning:theoretical framework and an algorithm [A]. Proceedings of the Fifteenth International Conference on Machine Learning, Morgan Kaufmann [C]. 1998. [6] FIRA. SimuroSot Overview[EB/OL]. http:/www. fira. net/soccer/ simurosot/overview. html.
