期刊文献+

基于强化学习的多智能体协作方法研究

Research of Multi-agent Coordination System Based on Reinforcement Learning
下载PDF
导出
摘要 为了在连续和动态的环境中处理智能体不断变化的需求,我们通过利用强化学习来研究多机器人推箱子问题,得到了一种智能体可以不需要其它智能体任何信息的情况下完成协作任务的方法。强化学习可以应用于合作和非合作场合,对于存在噪声干扰和通讯困难的情况,强化学习具有其它人工智能方法不可比拟的优越性。 In order to handle the changing requirements of continuous and dynamic environments, we use reinforcement learning techniques on a block pushing problem to show that agents can learn complimentary policies to fulfill a coordination task without any knowledge about each other. Reinforcement learning based coordination can be achieved in both cooperative and non-cooperative domains, and in domains with noisy communication channels and other stochastic characteristics that present a formidable challenge to using other coordination schemes.
作者 童亮 陆际联
出处 《计算机测量与控制》 CSCD 2005年第2期174-176,共3页 Computer Measurement &Control
基金 总装备部预研项目(40404070302)。
关键词 分布式人工智能 多智能体系统 多智能体协作方法 强化学习 <Keyword>multi-agent coordination system reinforcement learning
  • 引文网络
  • 相关文献

参考文献7

  • 1[1]WeiB G. Learning to coordinate actions in multi-agent systems[A]. Proceedings of the International Joint Conference on Artificial Intelligence[C]. 1993:311-316.
  • 2[2]Sutton R S. Integrated architecture for learning planning, and reacting based on approximate dynamic programming[A].Proceedings of the Seventh International Conference on Machine Learning[C]. 1993: 330-337.
  • 3[3]Watkins C. Learning from delayed rewards[D]. PhD thesis, King's College, Cambridge University,1990.
  • 4[4]Tan M. Multi-agent reinforcement learning: independent vs. cooperative agents[A]. In Proceedings of the Tenth International Conference on Machine Learning(ICML-93)[C].1993:335-341.
  • 5[5]Lin L J.Self-improving reactive agents based on reinforcement learning, planning and teaching[J].Machine Learning, 1992,8:293-321.
  • 6[6]Littman M L.Markov games as a framework for multi agent reinforcement learning[A]. Proceedings of the Eleventh International Conference on Machine Learning[C]. CA,1994:157-163.
  • 7[7]Warkins C,Dayan P. Technic note: Q-Learning[J]. Machine Learning, 1992,8:279-292.
;
使用帮助 返回顶部