%0 Journal Article
%T Research on the Combihation of Bayesian Learning and Reinforcement Learning<br>贝叶斯学习与强化学习结合技术的研究
%A CHEN Fei
%A WANG Ben-Nian
%A GAO Yang
%A CHEN Zhao-Qian
%A CHEN Shi-Fu
%A <br>陈飞
%A 王本年
%A 高阳
%A 陈兆乾
%A 陈世福
%J 计算机科学
%D 2006
%I 
%X A central problem in reinforcement learning is balancing exploration of untested actions against exploitation of actions that are known to be good.Bayesian learning is a probability method that makes optimal decision based on known probability distribution and recently observed data.So combination of Bayesian learning and reinforcement learning the agent can choose the strategy of exploration or exploitation based on its own experience and newly incoming knowledge.In this paper,we introduce single-agent Bayesian reinforcement learning and multi-agent Bayesian reinforce- ment learning.Single-agent Bayesian reinforcement learning includes Bayesian Q-learning,model-based Bayesian learn ing and Bayesian DP,and muhi-agent Bayesian reinforcement learning includes Bayesian imitation,Bayesian coordina- tion and Bayesian reinforcement learning for coalition formation under uncertainty.At last,some unsolved problems in Bayesian reinforcement learning are discussed.
%K Bayesian learning
%K Reinforcement learning
%K Single-agent
%K Multi-agent<br>贝叶斯学习
%K 强化学习
%K 单Agent
%K 多Agent
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=64A12D73428C8B8DBFB978D04DFEB3C1&aid=F49D482604BF90D8&yid=37904DC365DD7266&vid=27746BCEEE58E9DC&iid=0B39A22176CE99FB&sid=DABEF202280E7EF1&eid=6425DAE0271BB751&journal_id=1002-137X&journal_name=计算机科学&referenced_num=0&reference_num=32