%0 Journal Article
%T Multi-task Coalition Parallel Formation Strategy Based on Reinforcement Learning<br>基于强化学习的多任务联盟并行形成策略
%A JIANG Jian-Guo
%A SU Zhao-Pin
%A QI Mei-Bin
%A ZHANG Guo-Fu
%A <br>蒋建国
%A 苏兆品
%A 齐美彬
%A 张国富
%J 自动化学报
%D 2008
%I 
%X Agent coalition is an important manner of agents' coordination and cooperation.Forming a coalition,agents can enhance their ability to solve problems and obtain more utilities.In this paper,a novel multi-task coalition parallel formation strategy is presented,and the conclusion that the process of multi-task coalition formation is a Markov decision process is testified theoretically.Moreover,reinforcement learning is used to solve agents' behavior strategy,and the process of multi-task coalition parallel formation is described.In multi-task oriented domains,the strategy can effectively and parallel form multi-task coalitions.
%K Multi-task coalition
%K parallel formation
%K Markov decision process
%K reinforcement learning<br>Multi-task
%K coalition
%K parallel
%K formation
%K Markov
%K decision
%K process
%K reinforcement
%K learning
%K 强化学习
%K 多任务联盟
%K 并行
%K 策略
%K Reinforcement
%K Learning
%K Based
%K Strategy
%K Formation
%K Parallel
%K formation
%K oriented
%K behavior
%K reinforcement
%K learning
%K used
%K Markov
%K decision
%K process
%K novel
%K parallel
%K strategy
%K paper
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=E76622685B64B2AA896A7F777B64EB3A&aid=BA92167D8593102B45E671A253B292DD&yid=67289AFF6305E306&vid=339D79302DF62549&iid=38B194292C032A66&sid=31125890FF093250&eid=EA64BD0B2FF6E786&journal_id=0254-4156&journal_name=自动化学报&referenced_num=1&reference_num=14