Value Iteration Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems

doi:10.1109/TCYB.2015.2492242

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

	Value Iteration Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems
	Wei, Qinglai1 ; Liu, Derong 2; Lin, Hanquan1 ; Derong Liu
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
	2016-03-01
卷号	46 期号:3 页码:840-853
文章类型	Article
摘要	In this paper, a value iteration adaptive dynamic programming (ADP) algorithm is developed to solve infinite horizon undiscounted optimal control problems for discrete-time nonlinear systems. The present value iteration ADP algorithm permits an arbitrary positive semi-definite function to initialize the algorithm. A novel convergence analysis is developed to guarantee that the iterative value function converges to the optimal performance index function. Initialized by different initial functions, it is proven that the iterative value function will be monotonically nonincreasing, monotonically nondecreasing, or nonmonotonic and will converge to the optimum. In this paper, for the first time, the admissibility properties of the iterative control laws are developed for value iteration algorithms. It is emphasized that new termination criteria are established to guarantee the effectiveness of the iterative control laws. Neural networks are used to approximate the iterative value function and compute the iterative control law, respectively, for facilitating the implementation of the iterative ADP algorithm. Finally, two simulation examples are given to illustrate the performance of the present method.
关键词	Adaptive Critic Designs Adaptive Dynamic Programming (Adp) Approximate Dynamic Programming Neural Networks Neuro-dynamic Programming Optimal Control Reinforcement Learning Value Iteration
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCYB.2015.2492242
关键词[WOS]	OPTIMAL TRACKING CONTROL ; INPUT-OUTPUT DATA ; FEEDBACK-CONTROL ; CONTROL SCHEME ; LEARNING CONTROL ; HJB SOLUTION ; REINFORCEMENT ; APPROXIMATION ; ALGORITHM ; NETWORKS
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61533017 ; 61273140 ; 61374105 ; 61233001)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000370963500022
引用统计	被引频次：304[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/173211/11355
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
通讯作者	Derong Liu
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.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,Liu, Derong,Lin, Hanquan,et al. Value Iteration Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems[J]. IEEE TRANSACTIONS ON CYBERNETICS,2016,46(3):840-853.
APA	Wei, Qinglai,Liu, Derong,Lin, Hanquan,&Derong Liu.(2016).Value Iteration Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems.IEEE TRANSACTIONS ON CYBERNETICS,46(3),840-853.
MLA	Wei, Qinglai,et al."Value Iteration Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems".IEEE TRANSACTIONS ON CYBERNETICS 46.3(2016):840-853.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
2016_CYB_Value itera（2015KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载