引用本文: | 蒋建国,苏兆品,张国富,夏 娜.多任务联盟形成中的Agent行为策略研究[J].控制理论与应用,2008,25(5):853~856.[点击复制] |
JIANG Jian-guo,SU Zhao-pin,ZHANG Guo-fu,XIA Na.Agent-behavior strategy in serial multi-task coalition formation[J].Control Theory and Technology,2008,25(5):853~856.[点击复制] |
|
多任务联盟形成中的Agent行为策略研究 |
Agent-behavior strategy in serial multi-task coalition formation |
摘要点击 1391 全文点击 1181 投稿时间:2007-03-23 修订日期:2007-12-25 |
查看全文 查看/发表评论 下载PDF阅读器 |
DOI编号 |
2008,25(5):853-856 |
中文关键词 串行多任务 联盟 Agent行为策略 Q-学习 |
英文关键词 serial multi-task coalitions Agent behavior strategy Q-learning |
基金项目 国家自然科学基金资助项目(60474035); 国家教育部博士点基金资助项目(20060359004); 安徽省自然科学基金资助项目(070412035). |
|
中文摘要 |
Agent联盟是多Agent系统中一种重要的合作方式, 联盟形成是其研究的关键问题. 本文提出一种串行多任务联盟形成中的Agent行为策略, 首先论证了Agent合作求解多任务的过程是一个Markov决策过程, 然后基于Q-学习求解单个Agent的最优行为策略. 实例表明该策略在面向多任务的领域中可以快速、有效地串行形成多个任务求解联盟. |
英文摘要 |
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. |
|
|
|
|
|