A System Improving Reinforcement Learning Agents' Policies with two types of Mixture Models of Bayesian Networks
A System Improving Reinforcement Learning Agents' Policies with two types of Mixture Models of Bayesian Networks
复制标题
一种利用两种贝叶斯网络混合模型改进强化学习代理策略的系统
DOI:
--
复制
发表时间:
2005
期刊:
影响因子:
--
通讯作者:
Daisuke Kitakoshi
中科院分区:
文献类型:
--
作者:
J. Motomura;et. al.;J. Motomura;M. Shimizu;内田 努;永山 昌史;T.Uchida;M.Nagayama;Hiroyuki Shioya and Kazutoshi Gohara;H.Shioya;K.Gohara;M.Uchida;D.Kitakoshi;Daisuke Kitakoshi
DOI:
10.20965/jaciii.2003.p0276
发表时间:
2003
期刊:
J. Adv. Comput. Intell. Intell. Informatics
影响因子:
--
作者:
D. Kitakoshi;H. Shioya;M. Kurihara
通讯作者:
M. Kurihara