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

doi:10.1109/TSMC.2016.2623766

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

	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
发表期刊	IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
	2018-06-01
卷号	48 期号:6 页码:875-891
文章类型	Article
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.
关键词	Adaptive Critic Designs Adaptive Dynamic Programming (Adp) Approximate Dynamic Programming Local Iteration Neural Networks Neuro-dynamic Programming Nonlinear Systems Optimal Control
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TSMC.2016.2623766
关键词[WOS]	OPTIMAL TRACKING CONTROL ; OPTIMAL-CONTROL DESIGN ; NONLINEAR-SYSTEMS ; POLICY ITERATION ; CONTROL SCHEME ; FEEDBACK-CONTROL ; LEARNING CONTROL ; ALGORITHM ; REINFORCEMENT ; GAMES
收录类别	SCI
语种	英语
项目资助者	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)
WOS研究方向	Automation & Control Systems ; Computer Science
WOS类目	Automation & Control Systems ; Computer Science, Cybernetics
WOS记录号	WOS:000432401600005
引用统计	被引频次：118[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/173211/13632
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.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
第一作者单位	中国科学院自动化研究所
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.