期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

群体环境下基于随机对策的多Agent局部学习算法

Local Learning Algorithm for Multi-agent Based on Stochastic Games under Group Environment
下载PDF
导出
摘要 基于群体环境中个体agent局部感知和交互的生物原型,提出一种随机对策框架下的多agent局部学习算法.算法在与局部环境交互中采用贪婪策略最大化自身利益.分别在零和、一般和的单个平衡点和多个平衡点情形下改进了Nash-Q学习算法;提出了行为修正方法,并证明了算法收敛、计算复杂度降低. A local learning algorithm for multi-agent-based stochastic games is proposed in light of the fact that the individual performs local perception and interaction in group. In the algorithm, every agent adopts greedy policy to maximize- its payoff when interacting with the environment. The Nash-Q earning algorithm is improved respectively in situations of zero-sum, general-sum games with only one equilibrium or multi-equilibrium. Besides, the method to modify the behavior is proposed, and it is proved that the algorithm is convergent and the computing complexity is reduced.
作者 尹怡欣 江道平 班晓娟 孟祥嵩
机构地区 北京科技大学信息工程学院
出处 《信息与控制》 CSCD 北大核心 2008年第6期703-708,共6页 Information and Control
基金 国家自然科学基金资助项目(60503024 60374032)
关键词 多AGENT学习 随机对策 Nash—Q 局部学习 multi-agent learning stochastic game Nash-Q local Jearning
分类号 TP391.9 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献10

  • 1Wang B N, Gao Y, Chen Z Q, et al. A two-layered multi-agent reinforcement learning model and algorithm [J]. Journal of Network and Computer Applications, 2007, 30(4): 1366- 1376.
  • 2Littman M L. Markov games as a framework for multi-agent reinforcement learning [A]. Proceedings of the 11th International Conference on Machine Learning [C]. San Mateo, CA, USA: Morgan Kaufmann, 1994. 157-163.
  • 3Hu J, Wellman M E Experimental results on Q-learning for general-sam stochastic games [A]. Proceedings' of the Seventeenth International Conference on Machine Learning [C]. San Mateo, CA, USA: Morgan Kaufmarm, 2000. 407-414.
  • 4Ishii S, Yoshida W, Yoshimoto J. Control of exploitation-exploration meta-parameter in reinforcement learning [J]. Neural Networks, 2002, 15(4-6): 665-687.
  • 5Reynolds C W. Flocks, herds, and schools: A distributed behavioral model [J]. Computer Graphics, 1987, 21(4): 25-34.
  • 6Watkins C J C H, Dayan P. Q-learning [J]. Machine Learning, 1992, 8(3-4): 279-292.
  • 7Filar J A, Vrieze K. Competitive Markov Decision Processes [M]. New York, USA: Springer, 1996.
  • 8Shapley L S. Stochastic games [A]. Proceedings of the National Academy of Sciences of the United States of America [C]. Princeton, NJ, USA: Princeton University Press, 1953. 1095-1100.
  • 9Fink A M. Equilibrium in a stochastic n-person game [J]. Journal of Science in Hiroshima University, 1964, A128(1): 89-93.
  • 10Bowling M, Veloso M. Multiagent learning using a variable learning rate [J]. Artificial Intelligence, 2002, 136(2): 215-250.
信息与控制
2008年 第6期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部