Off-policy neuro-optimal control for unknown complex-valued nonlinear systems based on policy iteration

doi:10.1007/s00521-015-2144-0

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 > 平行控制

	Off-policy neuro-optimal control for unknown complex-valued nonlinear systems based on policy iteration
	Song, Ruizhuo 1; Wei, Qinglai2 ; Xiao, Wendong 1
刊名	NEURAL COMPUTING & APPLICATIONS
	2017-06-01
卷号	28 期号:6 页码:1435-1441
关键词	Adaptive Dynamic Programming Approximate Dynamic Programming Adaptive Critic Designs Optimal Control
DOI	10.1007/s00521-015-2144-0
文献子类	Article
英文摘要	This paper establishes an optimal control of unknown complex-valued system. Policy iteration is used to obtain the solution of the Hamilton-Jacobi-Bellman equation. Off-policy learning allows the iterative performance index and iterative control to be obtained by completely unknown dynamics. Critic and action networks are used to get the iterative control and iterative performance index, which execute policy evaluation and policy improvement. Asymptotic stability of the closed-loop system and the convergence of the iterative performance index function are proven. By Lyapunov technique, the uniformly ultimately bounded of the weight error is proven. Simulation study demonstrates the effectiveness of the proposed optimal control method.
WOS关键词	OPTIMAL TRACKING CONTROL ; CONTINUOUS-TIME SYSTEMS ; MULTIOBJECTIVE OPTIMAL-CONTROL ; ADAPTIVE OPTIMAL-CONTROL ; OPTIMAL-CONTROL SCHEME ; FEEDBACK-CONTROL ; NETWORK ; ALGORITHM ; DYNAMICS ; DESIGN
WOS研究方向	Computer Science
语种	英语
WOS记录号	WOS:000403939000019
资助机构	National Natural Science Foundation of China(61304079 ; Fundamental Research Funds for the Central Universities(FRF-TP-15-056A3) ; Open Research Project from SKLMCCS(20150104) ; 61374105)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/13640]
专题	复杂系统管理与控制国家重点实验室_平行控制
作者单位	1.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Song, Ruizhuo,Wei, Qinglai,Xiao, Wendong. Off-policy neuro-optimal control for unknown complex-valued nonlinear systems based on policy iteration[J]. NEURAL COMPUTING & APPLICATIONS,2017,28(6):1435-1441.
APA	Song, Ruizhuo,Wei, Qinglai,&Xiao, Wendong.(2017).Off-policy neuro-optimal control for unknown complex-valued nonlinear systems based on policy iteration.NEURAL COMPUTING & APPLICATIONS,28(6),1435-1441.
MLA	Song, Ruizhuo,et al."Off-policy neuro-optimal control for unknown complex-valued nonlinear systems based on policy iteration".NEURAL COMPUTING & APPLICATIONS 28.6(2017):1435-1441.