Online Reinforcement Learning by Bayesian Inference
Xia ZP(夏中谱); Dongbin Zhao
2015-07
会议名称International Joint Conference on Neural Networks
会议录名称Proceedings of International Joint Conference on Neural Networks 2015
会议日期2015年7月
会议地点Ireland
摘要Policy evaluation has long been one of the core  issues of the online reinforcement learning, especially in the continuous state domain. In this paper, the issue is addressed by employing Gaussian processes to represent the action value function from the probability perspective. By modeling the return as a stochastic variable, the action value function can sequentially update according to observed variables such as state and reward by Bayesian inference during the policy evaluation. The update rule shows that it is a temporal difference learning method with the learning rate determined by the uncertainty of a collected sample. Incorporating the policy evaluation method with the E-greedy action selection method, we propose an online reinforcement learning algorithm referred as to Bayesian-SARSA. It is tested on some benchmark problems and the empirical results verifies its effectiveness.
关键词Reinforcement Learning Bayesian Inference Gaussian Processes
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11434
专题复杂系统管理与控制国家重点实验室_智能化团队
通讯作者Dongbin Zhao
推荐引用方式
GB/T 7714
Xia ZP,Dongbin Zhao. Online Reinforcement Learning by Bayesian Inference[C],2015.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
2015. IJCNN_XiaZhao.(751KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Xia ZP(夏中谱)]的文章
[Dongbin Zhao]的文章
百度学术
百度学术中相似的文章
[Xia ZP(夏中谱)]的文章
[Dongbin Zhao]的文章
必应学术
必应学术中相似的文章
[Xia ZP(夏中谱)]的文章
[Dongbin Zhao]的文章
相关权益政策
暂无数据
收藏/分享
文件名: 2015. IJCNN_XiaZhao.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。