All Title Author
Keywords Abstract


基于边界样本协调的多智能体合作学习

, PP. 111-115

Keywords: 多智能体系统,强化学习,多智能体合作

Full-Text   Cite this paper   Add to My Lib

Abstract:

针对Q学习状态空间非常大,导致收敛速度非常慢的问题,给出一种基于边界样本协调的多智能体在线合作学习方法,使得智能体在特定的子空间上进行特化并通过边界状态上的开关函数相互协调,从而能够较快地学习到局部最优.仿真实验表明该方法能够取得比全局学习更好的在线学习性能.

References

[1]  Han Wei, Chen Youguang, Jiang Changhua. An InternalInference Based Multiagent Learning Method. Pattern Recognition and Artificial Intelligence, 2007, 20(2): 254260 (in Chinese) (韩 伟,陈优广,姜昌华. 基于内省推理的多agent在线学习方法.模式识别与人工智能, 2007, 20(2): 254260)
[2]  Luo Qing, Li Zhijun, Lü Tiansheng. MultiAgent Reinforcement Learning in Complex Environment. Journal of Shanghai Jiaotong University, 2002, 36(3): 302305 (in Chinese) (罗 清,李智军,吕恬生.复杂环境中的多智能体强化学习.上海交通大学学报, 2002, 36(3): 302305)
[3]  Du Chunxia, Gao Yun, Zhang Wen. QLearning with Prior Knowledge in MultiAgent Systems. Journal of Tsinghua University: Science and Technology, 2005, 45(7): 981984 (in Chinese) (杜春侠,高 云,张 文.多智能体系统中具有先验知识的Q学习算法.清华大学学报:自然科学版, 2005, 45(7): 981984)
[4]  Han Wei. MultiAgent Learning and Negotiation in Electronic MarketPlaces. Ph.D Dissertation. Shanghai, China: East China Normal University. College of Information Science and Technology, 2006: 7791 (in Chinese) (韩 伟.电子市场环境下的多智能体学习与协商.博士学位论文.上海:华东师范大学.信息科学技术学院, 2006: 7791)
[5]  Sun R, Peterson T. Multiagent Reinforcement Learning: Weighting and Partitioning. Neural Networks, 1999, 20(3): 727753
[6]  Hougen D F, Gini M, Slagle J. Partitioning Input Space for Reinforcement Learning for Control // Proc of the IEEE International Conference on Neural Networks. Houston, USA, 1997: 755760
[7]  Lee I S K, Lau H Y K. Adaptive State Space Partitioning for Reinforcement Learning. Engineering Applications of Artificial Intelligence, 2004, 17(3): 577588
[8]  Tesauro G J. Temporal Difference Learning and TDGammon. Communications of the ACM, 1995, 38(3): 5868
[9]  Baird L C. Residual Algorithms: Reinforcement Learning with Function Approximation // Proc of the 12th International Conference on Machine Learning. Tahoe City, USA, 1995: 3037
[10]  Liu J. Autonomous Agents and Multiagent Systems. River Edge, USA: World Scientific Publishing, 2001
[11]  Han Wei. Intelligent Pricing Algorithm Based on Multiagent Learning. Computer Engineering and Applications, 2007, 43(6): 1719 (in Chinese) (韩 伟.基于情节序列训练的电子市场智能定价算法.计算机工程与应用, 2007, 43(6): 1719)
[12]  Han Wei, Han Zhongyuan. Mutiagent Learning Based on BlackBoard Model. Computer Engineering, 2007, 33(22): 4244,47 (in Chinese) (韩 伟,韩忠愿.基于黑板模型的多智能体合作学习.计算机工程, 2007, 33(22): 4244,47)

Full-Text

comments powered by Disqus