Discrete-Time Local Value Iteration Adaptive Dynamic Programming: Admissibility and Termination Analysis

doi:10.1109/TNNLS.2016.2593743

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: Admissibility and Termination Analysis
	Wei, Qinglai1 ; Liu, Derong 2; Lin, Qiao1
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2017-11-01
卷号	28 期号:11 页码:2490-2502
文章类型	Article
摘要	In this paper, a novel local value iteration adaptive dynamic programming (ADP) algorithm is developed to solve infinite horizon optimal control problems for discrete-time nonlinear systems. The focuses of this paper are to study admissibility properties and the termination criteria of discrete-time local value iteration ADP algorithms. In the discrete-time local value iteration ADP algorithm, the iterative value functions and the iterative control laws are both updated in a given subset of the state space in each iteration, instead of the whole state space. For the first time, admissibility properties of iterative control laws are analyzed for the local value iteration ADP algorithm. New termination criteria are established, which terminate the iterative local ADP algorithm with an admissible approximate optimal control law. Finally, simulation results 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 Neurodynamic Programming Nonlinear Systems Optimal Control
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TNNLS.2016.2593743
关键词[WOS]	OPTIMAL TRACKING CONTROL ; ZERO-SUM GAME ; NONLINEAR-SYSTEMS ; FEEDBACK-CONTROL ; CONTROL SCHEME ; LEARNING CONTROL ; REINFORCEMENT ; ALGORITHM ; CONVERGENCE ; NETWORKS
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61233001 ; 61273140 ; 61374105 ; 61533017 ; U1501251)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号	WOS:000413403900003
引用统计	被引频次：28[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/173211/13631
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 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, Qiao. Discrete-Time Local Value Iteration Adaptive Dynamic Programming: Admissibility and Termination Analysis[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2017,28(11):2490-2502.
APA	Wei, Qinglai,Liu, Derong,&Lin, Qiao.(2017).Discrete-Time Local Value Iteration Adaptive Dynamic Programming: Admissibility and Termination Analysis.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,28(11),2490-2502.
MLA	Wei, Qinglai,et al."Discrete-Time Local Value Iteration Adaptive Dynamic Programming: Admissibility and Termination Analysis".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 28.11(2017):2490-2502.