Continuous-Time Stochastic Policy Iteration of Adaptive Dynamic Programming

doi:10.1109/TSMC.2023.3284612

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	Continuous-Time Stochastic Policy Iteration of Adaptive Dynamic Programming
	Wei, Qinglai 4,5; Zhou, Tianmin 5; Lu, Jingwei 2,3,5; Liu, Yu 6; Su, Shuai 1; Xiao, Jun 4
刊名	IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
	2023-06-30
页码	13
关键词	Adaptive dynamic programming (ADP) Hamilton-Jacobi-Bellman equation (HJBE) nonlinear stochastic system stochastic policy iteration (PI)
ISSN号	2168-2216
DOI	10.1109/TSMC.2023.3284612
通讯作者	Wei, Qinglai(qinglai.wei@ia.ac.cn) ; Xiao, Jun(xiaojun@ucas.ac.cn)
英文摘要	In this article, we study the optimal control problem of continuous-time (CT) time-invariant nonlinear systems with stochastic nonlinear disturbances. A new stochastic adaptive dynamic programming (ADP) method is developed to solve the Hamilton-Jacobi-Bellman equation (HJBE). Under the conditional expectation, the value function and the control law are successively approximated simultaneously. The asymptotic stability of the closed-loop stochastic system in probability is analyzed by the stochastic Lyapunov direct method, and the convergence of the developed ADP method is given. Finally, four simulations illustrate the effectiveness of the developed method.
资助项目	National Key Research and Development Program of China[2021YFE0206100] ; Science and Technology Development Fund of the Macao Special Administrative Region[FDCT-22-009-MISE] ; National Natural Science Foundation of China[62073321] ; National Natural Science Foundation of China[U22A2046] ; National Natural Science Foundation of China[52172322] ; State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University[RCS2021K005]
WOS关键词	SYSTEMS ; STABILIZATION ; FEEDBACK
WOS研究方向	Automation & Control Systems ; Computer Science
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001025540300001
资助机构	National Key Research and Development Program of China ; Science and Technology Development Fund of the Macao Special Administrative Region ; National Natural Science Foundation of China ; State Key Laboratory of Rail Traffic Control and Safety, Beijing Jiaotong University
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/53618]
专题	多模态人工智能系统全国重点实验室
通讯作者	Wei, Qinglai; Xiao, Jun
作者单位	1.Beijing Jiaotong Univ, State Key Lab Rail Traff Control & Safety, Beijing 100044, Peoples R China 2.Qingdao Acad Intelligent Ind, Parallel Intelligence Innovat Res Ctr, Qingdao 266109, Peoples R China 3.Macau Univ Sci & Technol, Inst Syst Engn, Taipa, Macau, Peoples R China 4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 5.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 6.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wei, Qinglai,Zhou, Tianmin,Lu, Jingwei,et al. Continuous-Time Stochastic Policy Iteration of Adaptive Dynamic Programming[J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,2023:13.
APA	Wei, Qinglai,Zhou, Tianmin,Lu, Jingwei,Liu, Yu,Su, Shuai,&Xiao, Jun.(2023).Continuous-Time Stochastic Policy Iteration of Adaptive Dynamic Programming.IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,13.
MLA	Wei, Qinglai,et al."Continuous-Time Stochastic Policy Iteration of Adaptive Dynamic Programming".IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2023):13.