Continuous-Time Time-Varying Policy Iteration

doi:10.1109/TCYB.2019.2926631

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 智能化团队

	Continuous-Time Time-Varying Policy Iteration
	Wei, Qinglai 2,3; Liao, Zehua 2,3; Yang, Zhanyu 2,3; Li, Benkai 2,3; Liu, Derong 1
刊名	IEEE TRANSACTIONS ON CYBERNETICS
	2020-12-01
卷号	50 期号:12 页码:4958-4971
关键词	Optimal control Nonlinear systems Time-varying systems Mathematical model Dynamic programming Approximation algorithms Iterative algorithms Adaptive critic designs adaptive dynamic programming (ADP) neuro-dynamic programming nonlinear systems optimal control policy iteration
ISSN号	2168-2267
DOI	10.1109/TCYB.2019.2926631
通讯作者	Wei, Qinglai(qinglai.wei@ia.ac.cn)
英文摘要	A novel policy iteration algorithm, called the continuous-time time-varying (CTTV) policy iteration algorithm, is presented in this paper to obtain the optimal control laws for infinite horizon CTTV nonlinear systems. The adaptive dynamic programming (ADP) technique is utilized to obtain the iterative control laws for the optimization of the performance index function. The properties of the CTTV policy iteration algorithm are analyzed. Monotonicity, convergence, and optimality of the iterative value function have been analyzed, and the iterative value function can be proven to monotonically converge to the optimal solution of the Hamilton-Jacobi-Bellman (HJB) equation. Furthermore, the iterative control law is guaranteed to be admissible to stabilize the nonlinear systems. In the implementation of the presented CTTV policy algorithm, the approximate iterative control laws and iterative value function are obtained by neural networks. Finally, the numerical results are given to verify the effectiveness of the presented method.
资助项目	National Natural Science Foundation of China[61503379] ; National Natural Science Foundation of China[61722312] ; National Natural Science Foundation of China[61533017] ; National Natural Science Foundation of China[U1501251]
WOS关键词	APPROXIMATE OPTIMAL-CONTROL ; ADAPTIVE OPTIMAL-CONTROL ; NONLINEAR-SYSTEMS ; FEEDBACK-CONTROL ; DESIGN ; INPUT ; GAMES ; SUM
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:000597151500009
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/42667]
专题	自动化研究所_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	Wei, Qinglai
作者单位	1.Guangdong Univ Technol, Sch Automat, Guangzhou 510006, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Wei, Qinglai,Liao, Zehua,Yang, Zhanyu,et al. Continuous-Time Time-Varying Policy Iteration[J]. IEEE TRANSACTIONS ON CYBERNETICS,2020,50(12):4958-4971.
APA	Wei, Qinglai,Liao, Zehua,Yang, Zhanyu,Li, Benkai,&Liu, Derong.(2020).Continuous-Time Time-Varying Policy Iteration.IEEE TRANSACTIONS ON CYBERNETICS,50(12),4958-4971.
MLA	Wei, Qinglai,et al."Continuous-Time Time-Varying Policy Iteration".IEEE TRANSACTIONS ON CYBERNETICS 50.12(2020):4958-4971.