Discrete-Time Local Value Iteration Adaptive Dynamic Programming: Convergence Analysis

doi:10.1109/TSMC.2016.2623766

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

	Discrete-Time Local Value Iteration Adaptive Dynamic Programming: Convergence Analysis
	Wei, Qinglai1 ; Lewis, Frank L.2,3; Liu, Derong 4; Song, Ruizhuo 4; Lin, Hanquan1
刊名	IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
	2018-06-01
卷号	48 期号:6 页码:875-891
关键词	Adaptive Critic Designs Adaptive Dynamic Programming (Adp) Approximate Dynamic Programming Local Iteration Neural Networks Neuro-dynamic Programming Nonlinear Systems Optimal Control
DOI	10.1109/TSMC.2016.2623766
文献子类	Article
英文摘要	In this paper, convergence properties are established for the newly developed discrete-time local value iteration adaptive dynamic programming (ADP) algorithm. The present local iterative ADP algorithm permits an arbitrary positive semidefinite function to initialize the algorithm. Employing a state-dependent learning rate function, for the first time, the iterative value function and iterative control law can be updated in a subset of the state space instead of the whole state space, which effectively relaxes the computational burden. A new analysis method for the convergence property is developed to prove that the iterative value functions will converge to the optimum under some mild constraints. Monotonicity of the local value iteration ADP algorithm is presented, which shows that under some special conditions of the initial value function and the learning rate function, the iterative value function can monotonically converge to the optimum. Finally, three simulation examples and comparisons are given to illustrate the performance of the developed algorithm.
WOS关键词	OPTIMAL TRACKING CONTROL ; OPTIMAL-CONTROL DESIGN ; NONLINEAR-SYSTEMS ; POLICY ITERATION ; CONTROL SCHEME ; FEEDBACK-CONTROL ; LEARNING CONTROL ; ALGORITHM ; REINFORCEMENT ; GAMES
WOS研究方向	Automation & Control Systems ; Computer Science
语种	英语
WOS记录号	WOS:000432401600005
资助机构	National Natural Science Foundation of China(61233001 ; Fundamental Research Funds for the Central Universities(FRF-TP-15-056A3) ; Open Research Project from SKLMCCS(20150104) ; 61273140 ; 61374105 ; 61503379 ; 61304079 ; 61673054 ; 61533017 ; U1501251)
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/13632]
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.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Texas Arlington, UTA Res Inst, Arlington, TX 76118 USA 3.Northeastern Univ, Shenyang 110036, Liaoning, Peoples R China 4.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
推荐引用方式 GB/T 7714	Wei, Qinglai,Lewis, Frank L.,Liu, Derong,et al. Discrete-Time Local Value Iteration Adaptive Dynamic Programming: Convergence Analysis[J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,2018,48(6):875-891.
APA	Wei, Qinglai,Lewis, Frank L.,Liu, Derong,Song, Ruizhuo,&Lin, Hanquan.(2018).Discrete-Time Local Value Iteration Adaptive Dynamic Programming: Convergence Analysis.IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,48(6),875-891.
MLA	Wei, Qinglai,et al."Discrete-Time Local Value Iteration Adaptive Dynamic Programming: Convergence Analysis".IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 48.6(2018):875-891.