期刊文献+

基于强化学习的多机器人协作 被引量:3

Multi-Robot Cooperation Based on Reinforcement Learning
下载PDF
导出
摘要 提出了一种动态环境下多个机器人获取合作行为的强化学习方法,该方法采用基于瞬时奖励的Q-学习完成单个机器人的学习,并利用人工势场法的思想确定不同机器人的学习顺序,在此基础上采用交替学习来完成多机器人的学习过程。试验结果表明所提方法的可行性和有效性。 In this paper,a kind of reinforcement learning method is addressed to obtain cooperative behaviors for multiple robots under dynamic environment.The proposed learning method adopts Q-learning with immediate reward,and determines learning order for different robots by virtue of the idea of artificial potential field.Based on these modifications,an alternative learning process is introduced to finish the learning process among multiple robots.Experimental results have shown the feasibility and validity of the given approach.
出处 《计算机工程与应用》 CSCD 北大核心 2005年第28期10-12,90,共4页 Computer Engineering and Applications
基金 国家自然科学基金资助项目(编号:69985002)
关键词 多机器人系统 机器人足球 强化学习 协作 multi-robot system,robot soccer,reinforcement learning,cooperation
  • 相关文献

参考文献1

二级参考文献8

  • 1Stone, P., Veloso, M. Team-Partitioned, opaque-transition reinforcement learning.In: Asada, M., Kitano, H., eds, Robocup-98: Robot Soccer World CupII. Berlin: SpringerVerlag, 1999.
  • 2Kim, Do-Yoon, Chung, Myung Jin. Path planning for multi-mobil robots in the dynamicenvironment. In: Proceedings of the Micro-Robot World Cup Soccer Tournament. 1996. 127~132.
  • 3Noda, I., Matsubara, H., Hiraki, K., et al. Soccer server: a tool for research onmultiagent systems. Applied Artificial Intelligence, 1998,12:25~27.
  • 4Kitano, H., Asada, M., Kuniyoshi,Y., et al. A challenge problem. AI Magazine, 1997,18(1):73-85.
  • 5Stone, P., Veloso, M. Using machine learning in the soccer server. In: Proceedingsof the IROS Workshop on Robocup. Osaka, Japan, 1996. 105~203.
  • 6Uchibe, E., Asada, M., Hosoda, K. State space construction for behavior acquisitionin multi-agent environments with vision and action. In: Proceedings of the InternationalConference on Computer Vision. 1998. 870~875.
  • 7Salustowicz, R.P., Wiering, M.A., Schmidhuber, J. Learning team strategies: soccercase studies. Machine Learning, 1998,33: 263~282.
  • 8Sandholm, T.W., Crites, R.H. On multiagent Q-learning in a semi-competition domain.In: Weib, G., Sen, S., eds. Adaptation and Learning in Multiagent Systems. Berlin:Springer-Verlag, 1996. 188~190.

共引文献2

同被引文献42

引证文献3

二级引证文献5

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