Online reinforcement learning control by Bayesian inference

doi:10.1049/iet-cta.2015.0669

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 深度强化学习

	Online reinforcement learning control by Bayesian inference
	Xia, Zhongpu; Zhao, Dongbin; Dongbin Zhao
发表期刊	IET CONTROL THEORY AND APPLICATIONS
	2016-08-08
卷号	10 期号:12 页码:1331-1338
文章类型	Article
摘要	Reinforcement learning offers a promising way for self-learning control of an unknown system, but it involves the issues of policy evaluation and exploration, especially in the domain of continuous state. In this study, these issues are addressed from the perspective of probability. It models the action value function as the latent variable of Gaussian process, while the reward as the observed variable. Then an online approach is proposed to update the action value function by Bayesian inference. Taking an advantage of the proposed framework, a prior knowledge can be incorporated into the action value function, and thus an efficient exploration strategy is presented. At last, the Bayesian-state-action-reward-state-action algorithm is tested on some benchmark problems and empirical results show its effectiveness.
关键词	Learning Systems Bayes Methods Gaussian Processes Optimal Control Online Reinforcement Learning Control Bayesian Inference Self-learning Control Probability Action Value Function Gaussian Process Bayesian-state-action-reward-state-action Algorithm
WOS标题词	Science & Technology ; Technology
DOI	10.1049/iet-cta.2015.0669
关键词[WOS]	AFFINE NONLINEAR-SYSTEMS ; FEEDBACK-CONTROL ; TIME-SYSTEMS ; ALGORITHM ; ITERATION
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China (NSFC)(61273136 ; 61573353 ; 61533017)
WOS研究方向	Automation & Control Systems ; Engineering ; Instruments & Instrumentation
WOS类目	Automation & Control Systems ; Engineering, Electrical & Electronic ; Instruments & Instrumentation
WOS记录号	WOS:000381410000003
引用统计	被引频次：5[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11432
专题	多模态人工智能系统全国重点实验室_深度强化学习
通讯作者	Dongbin Zhao
作者单位	Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Xia, Zhongpu,Zhao, Dongbin,Dongbin Zhao. Online reinforcement learning control by Bayesian inference[J]. IET CONTROL THEORY AND APPLICATIONS,2016,10(12):1331-1338.
APA	Xia, Zhongpu,Zhao, Dongbin,&Dongbin Zhao.(2016).Online reinforcement learning control by Bayesian inference.IET CONTROL THEORY AND APPLICATIONS,10(12),1331-1338.
MLA	Xia, Zhongpu,et al."Online reinforcement learning control by Bayesian inference".IET CONTROL THEORY AND APPLICATIONS 10.12(2016):1331-1338.

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
2016. IETCTA_XiaZhao（1559KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载