%0 Journal Article
%T Agent-behavior strategy in serial multi-task coalition formation<br>多任务联盟形成中的Agent行为策略研究
%A JIANG Jian-guo
%A SU Zhao-pin
%A ZHANG Guo-fu
%A XIA Na
%A <br>蒋建国
%A 苏兆品
%A 张国富
%A 夏 娜
%J 控制理论与应用
%D 2008
%I 
%X Agent-coalition is an important approach to agent-coordination and cooperation, in which the coalition formation is a key topic. Existing researches are restricted in single-task environments, and the results are not applied to multi-task environments. In this paper, a new agent behavior strategy in serial multi-task coalition formation for problemsolving is presented. The conclusion shows that the agent-task selection is a Markov Decision Process. The Q-learning is used to optimize the behavior strategy for a single agent, and the cooperative multi-agent reinforcement learning improves the learning rate. Experiments prove that the strategy can effectively and serially form coalitions for multi-task.
%K serial multi-task
%K coalitions
%K Agent behavior strategy
%K Q-learning<br>串行多任务
%K 联盟
%K Agent行为策略
%K Q-学习
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=970898A57DFC021F93AB51667BAED7F7&aid=94D88F02DC10E8889B40EE3C7522E45F&yid=67289AFF6305E306&vid=C5154311167311FE&iid=94C357A881DFC066&sid=970314C3B74F6C4D&eid=353B961D86F026C0&journal_id=1000-8152&journal_name=控制理论与应用&referenced_num=1&reference_num=10