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.
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)。