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

基于两层Q-Learning算法的多智能体协作方法研究

Research on Intelligent Multi-Agent Cooperation Based on Two Layer Q-Learning Algorithm
下载PDF
导出
摘要 为使多智能体系统更能适应复杂环境,将分层方法引入强化学习。把两层Q-Learning强化学习算法用于4个智能体协作推动圆盘物体,在未知环境中实现路径规划的计算机模拟中。仿真结果说明该方法的有效性和可行性。 In order to make the intelligent system better adapt the complex environment, brings the layering method into the reinforcement learning. The two layer Q-Learning method is used in the computer simulation of path planning for intelligent agents that cooperatively pushing a round dish in unknown environment. The result of simulation shows that this method is valid and feasible.
作者 王帅
机构地区 中国煤炭科工集团沈阳研究院
出处 《煤矿机电》 2013年第5期74-76,共3页 Colliery Mechanical & Electrical Technology
关键词 强化学习 Q学习 多智能体协作 路径规划 reinforcement learning Q-Learning intelligent multi-agent cooperation path planning
分类号 TP18 [自动化与计算机技术—控制理论与控制工程]
  • 相关文献

参考文献5

  • 1Stone P,Veloso M. Multi-agent systems: a survey from a machine learning perspective [ R ]. CMU CS technical report, No. CMU-CS- 97-103.
  • 2Sutton R S, Barto A G. Reinforcement Learning: An Introduction [ M]. Cambridge,MA: MIT Press,1998.
  • 3Watkins C, Dayan P. Q-learning[ J ]. Machine Learning, 1992,8 (3) :279-292.
  • 4陈雪江,杨东勇.基于强化学习的多智能体协作实现[J].浙江工业大学学报,2004,32(5):516-519. 被引量：1
  • 5Littman M L, Szepesvari C. A Generalized Reinforcement learning Model:Convergence and Application. In:Proc of the 13th Int'l Conf on Machine Learning. Bar, Italy: MorganKanfmann, 1996: 310.

二级参考文献13

  • 1Hu J,Michael Wellman P. Multiagent reinforcement learning: theoretical framework and an algorithm[A]. Proceedings.15th International Conf[C]. on Machine Learning, 1998. 242-250.
  • 2Claus Caroline,Boutilier Craig. The dynamics of reinforcement learning in cooperative multiagent systems[A]. Proc[C].Workshop on Multi-Agent Learning, 1997. 602-608.
  • 3Sutton R S,Barto A G. Reinforcement learning[M]. MIT Press ,1997.
  • 4Littman M L. Markov games as a framework for multi-agent reinforcement learning[J]. Proc 7th International Conference on Machine Learning , 1994, (1):157-163.
  • 5Littman M L, Szepesvari C. A generalized reinforcement-learning model: Convergence and applications[A]. Proc of the 13th Int'l Conf on Machine Learning[C]. Bari, Italy: Morgan Kanfmann, 1996. 310-318.
  • 6Piao S, Hong B. Fast reinforcement learning approach to cooperative behavior acquisition in multi-agent system[A]. Proceedings of the 2002 IEEE/RSJ International Conference on Intelligent Robots and Systems EPFL[C]. Lausanne ,Switzerland, 2002. 871-875.
  • 7Mataric M J. Reinforcement learning in the multi-robot domain[J]. Autonomous Robots, 1997, 4(1):73-83.
  • 8Stone P, Veloso M. Using machine learning in the soccer server[A]. Proceedings of the IROS-96 Workshop on RoboCup [C]. Osaka, 1996.
  • 9Suematsu N,Hayashi A. A multiagent reinforcement learning algorithm using extended optimal response[A]. Proceedings of the First International Joint Conference on Autonomous Agents & Multiagent Systems[C]. Bologna Italy, 2002. 370-377.
  • 10高阳,周志华,何佳洲,陈世福.基于Markov对策的多Agent强化学习模型及算法研究[J].计算机研究与发展,2000,37(3):257-263. 被引量：30
煤矿机电
2013年 第5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