%0 Journal Article
%T Reinforcement learning: survey of recent work<br>强化学习研究综述
%A CHEN Xue-song
%A YANG Yi-mina
%A <br>陈学松
%A 杨宜民a
%J 计算机应用研究
%D 2010
%I 
%X The problem of agent learning to act in an unknown world is both challenging and interesting. Reinforcement lear-ning has been successful at finding optimal control policies through trial-and-error interaction with dynamic environment. Its properties of self-improving and online learning make reinforcement learning become one of most important machine learning methods. The goal of this paper was to provide a comprehensive review of reinforcement learning about theory, algorithms and applications. First of all, this paper surveyed the foundation, model of environment of reinforcement learning. Discussed the convergence and generalization of the algorithms in the next. Then deeply discussed two representative selection of these algorithm, including discounted reward and average reward. Finally, provided some applications of reinforcement learning, and pointed out some challenges and problems of reinforcement learning.
%K reinforcement learning
%K multi-agent systems
%K Markov decision processes<br>强化学习
%K 多智能体
%K 马尔可夫决策过程
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=A9D9BE08CDC44144BE8B5685705D3AED&aid=3EC594780D9ACCCC443693B6C81B8D82&yid=140ECF96957D60B2&vid=DB817633AA4F79B9&iid=5D311CA918CA9A03&sid=D28BA532798ECC49&eid=8B96FBF5BCE341D5&journal_id=1001-3695&journal_name=计算机应用研究&referenced_num=0&reference_num=67