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

doi:10.1007/s00521-015-2144-0

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 复杂系统智能机理与平行控制团队

	Off-policy neuro-optimal control for unknown complex-valued nonlinear systems based on policy iteration
	Song, Ruizhuo 1; Wei, Qinglai2 ; Xiao, Wendong 1
发表期刊	NEURAL COMPUTING & APPLICATIONS
	2017-06-01
卷号	28 期号:6 页码:1435-1441
文章类型	Article
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.
关键词	Adaptive Dynamic Programming Approximate Dynamic Programming Adaptive Critic Designs Optimal Control
WOS标题词	Science & Technology ; Technology
DOI	10.1007/s00521-015-2144-0
关键词[WOS]	OPTIMAL TRACKING CONTROL ; CONTINUOUS-TIME SYSTEMS ; MULTIOBJECTIVE OPTIMAL-CONTROL ; ADAPTIVE OPTIMAL-CONTROL ; OPTIMAL-CONTROL SCHEME ; FEEDBACK-CONTROL ; NETWORK ; ALGORITHM ; DYNAMICS ; DESIGN
收录类别	SCI
语种	英语
项目资助者	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)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000403939000019
引用统计	被引频次：2[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/173211/13640
专题	多模态人工智能系统全国重点实验室_复杂系统智能机理与平行控制团队
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.