%0 Journal Article
%T Reinforcement Learning Model and Algorithm Based on Multi-agent Cooperation<br>多Agent协作的强化学习模型和算法
%A LIU Fei
%A ZENG Guang-Zhou
%A SONG Yan-Wei
%A <br>刘菲
%A 曾广周
%A 宋言伟
%J 计算机科学
%D 2006
%I 
%X The multi-agent cooperative learning process based on Reinforcement Learning is addressed and a new multi-agent cooperative learning model is proposed. Based on this model, a cooperative learning algorithm is introduced. This algorithm pays fully attention to multi-agent cooperative learning together simultaneity, so it can make each agent predict its action policy based on the estimation on its action's long-time reward. At last relevant decisions to be the best associated action policy is made. We conduct a series of empirical evaluation of the algorithm on the hunter-prey problem to validate its astringency. The result shows this algorithm is an efficient and fast method for multi-agent learning.
%K Cooperative learning
%K Reinforcement learning
%K Multi-agent learning
%K Learning model
%K Learning algorithm<br>协作学习
%K 强化学习
%K 多Agent学习
%K 学习模型
%K 学习算法
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=64A12D73428C8B8DBFB978D04DFEB3C1&aid=049A8FAB78ADDBC6&yid=37904DC365DD7266&vid=27746BCEEE58E9DC&iid=59906B3B2830C2C5&sid=3F0AF5EDBC960DB0&eid=4C100B7696CE9E24&journal_id=1002-137X&journal_name=计算机科学&referenced_num=0&reference_num=8