·100. 智能系统学报 第6卷 [9]王醒策，张汝波，顾国昌.基于强化学习的多机器人编队 参考文献： 方法研究[J].计算机工程，2002,28(6)：15-16， [1]CHONGJIE Z,LESSER V,SHENOY P.A multi-Agent WANG Xingce,ZHANG Rubo,GU Guochang.Research on learning approach to resource sharing across computing multi-Agent team formation based on reinforcement learning clusters[R].Computer Science Department,University of [J].Computer Engineering,2002,28(6):15-16. Massachusetts Computer Science Amherst UMass,UM-CS- [10]HU J,WELLMAN M P.Nash Q-learning for general-sum 2008035,2008. stochastic games [J].Journal of Machine Learning Re- [2]KO P C,LIN P C,YOU J A,et al.Multi-layer allocated search,2003,4:1039-1069. leaming based neural network for resource allocation optimi- [11]ALPAYDM E.机器学习导论[M].范明，等译.北京： zation[C]//Proceedings of the 9th Joint Conference on In- 北京工业出版社，2009：244255， formation Sciences(JCIS 2006).Taibei,China,2006:35- [12]LAGOUDAKIS M G,PARR R.Least-squares policy itera- 41. tion[J].Joural of Machine Leaming Research,2003 [3]TESAURO G.Online resource allocation using decomposi- (4):1107-1149. tional reinforcement learning [C]//Proceedings of AAAI [13]XU X,HU D W,LU X C.Kemel based least-squares pol- 2005.Pittsburgh,USA,2005:886-891. icy iteration[J].IEEE Transactions on Neural Networks, [4]LITTMAN M L,STONE P.Leading best-response strategies 2007,18(4):973992. in repeated games[C]//The 17th Annual International Joint 作者简介： Conference on Artificial Intelligence Workshop on Economic 连传强，男，1986年生，硕士研究生， Agents,Models,and Mechanism.Seattle,Washington, 主要研究方向为模式识别与机器学习. USA,2001:745-756. [5]HU J,WELLMAN M P.Multiagent reinforcement learning in stochastic games OL].Citeseer.ist.psu.edu/ hu99multiagent.Html,1999. [6]BUSONIU L,De SCHUTTER B,BABUSKA R.Multiagent reinforcement learning with adaptive state focus[C]//Pro- 徐昕，男，1974年生，研究员，博士， ceedings of the 17th Belgium-Netherlands Conference on Ar- 主要研究方向为增强学习、自适应动态 tificial Intelligence.Brussels,Belgium,2005:35-42. 规划理论和算法、智能移动机器人、智 [7]KOK J R,VLASSIS N.Collaborative multiagent reinforce- 能系统 ment leaming by payoff propagation[J].Joural of Machine Learning Research,2006,7:1789-1828. [8]杨佩，陈兆乾，陈世福.机器学习在RoboCup中的应用研 究[J].计算机科学，2003,30(6)：118-121. 吴军，男，1980年生，博士研究生. YANG Pei,CHEN Zhaoqian,CHEN Shifu.RoboCup 主要研究方向为多机器人系统、机器学 multi-Agent system machine-learning [J].Computer Sci- 习与智能系统。 ences,2003,30(6):118-121