%0 Journal Article
%T MULTI-AGENT LEARNING BASED ON GENERAL-SUM STOCHASTIC GAMES<br>基于一般和随机对策论框架下的多智能体学习
%A OU Hai-Tao
%A ZHANG Wei-Dong
%A XU Xiao-Ming
%A <br>欧海涛
%A 张卫东
%A 许晓鸣
%J 自动化学报
%D 2002
%I 
%X Q -learning from original single-agent framework is extended to non-cooperative multi-agent framework, and the theoretic framework of multi-agent learning is proposed under general-sum stochastic games with Nash equilibrium point as learning objective. We introduce a multi-agent Q -learning algorithm and prove its convergence under certain restriction, which is very important for the study and application of multi-agent system.
%K Multi-agent
%K Q
%K -learning
%K stochastic games
%K Nash equilibrium point<br>随机对策论
%K 多智能体学习
%K 学习算法
%K 强化学习
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=E76622685B64B2AA896A7F777B64EB3A&aid=8D1461EED7E7A791&yid=C3ACC247184A22C1&vid=D3E34374A0D77D7F&iid=38B194292C032A66&sid=F27A401E323B6FAD&eid=BA48F0B914ED890A&journal_id=0254-4156&journal_name=自动化学报&referenced_num=0&reference_num=6