Adaptive Dynamic Programming for Discrete-Time Zero-Sum Games

doi:10.1109/TNNLS.2016.2638863

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

	Adaptive Dynamic Programming for Discrete-Time Zero-Sum Games
	Wei, Qinglai1,2 ; Liu, Derong 3; Lin, Qiao1,2 ; Song, Ruizhuo 3
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2018-04-01
卷号	29 期号:4 页码:957-969
关键词	Adaptive Critic Designs Adaptive Dynamic Programming (Adp) Approximate Dynamic Programming Neurodynamic Programming Optimal Control Zero-sum Game
DOI	10.1109/TNNLS.2016.2638863
文献子类	Article
英文摘要	In this paper, a novel adaptive dynamic programming (ADP) algorithm, called "iterative zero-sum ADP algorithm," is developed to solve infinite-horizon discrete-time two-player zero-sum games of nonlinear systems. The present iterative zero-sum ADP algorithm permits arbitrary positive semidefinite functions to initialize the upper and lower iterations. A novel convergence analysis is developed to guarantee the upper and lower iterative value functions to converge to the upper and lower optimums, respectively. When the saddle-point equilibrium exists, it is emphasized that both the upper and lower iterative value functions are proved to converge to the optimal solution of the zero-sum game, where the existence criteria of the saddle-point equilibrium are not required. If the saddle-point equilibrium does not exist, the upper and lower optimal performance index functions are obtained, respectively, where the upper and lower performance index functions are proved to be not equivalent. Finally, simulation results and comparisons are shown to illustrate the performance of the present method.
WOS关键词	OPTIMAL TRACKING CONTROL ; AFFINE NONLINEAR-SYSTEMS ; H-INFINITY CONTROL ; UNKNOWN DYNAMICS ; ITERATION ALGORITHM ; LEARNING ALGORITHM ; DIFFERENTIAL-GAMES ; FEEDBACK-CONTROL ; LINEAR-SYSTEMS ; CONTROL SCHEME
WOS研究方向	Computer Science ; Engineering
语种	英语
WOS记录号	WOS:000427859600016
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/13627]
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 Chinese Acad Sci, Beijing 100049, Peoples R China 3.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China
推荐引用方式 GB/T 7714	Wei, Qinglai,Liu, Derong,Lin, Qiao,et al. Adaptive Dynamic Programming for Discrete-Time Zero-Sum Games[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(4):957-969.
APA	Wei, Qinglai,Liu, Derong,Lin, Qiao,&Song, Ruizhuo.(2018).Adaptive Dynamic Programming for Discrete-Time Zero-Sum Games.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(4),957-969.
MLA	Wei, Qinglai,et al."Adaptive Dynamic Programming for Discrete-Time Zero-Sum Games".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.4(2018):957-969.