Discrete-Time Stable Generalized Self-Learning Optimal Control With Approximation Errors

doi:10.1109/TNNLS.2017.2661865

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 Stable Generalized Self-Learning Optimal Control With Approximation Errors
	Wei, Qinglai1,2 ; Li, Benkai1 ; Song, Ruizhuo 3
发表期刊	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2018-04-01
卷号	29 期号:4 页码:1226-1238
文章类型	Article
摘要	In this paper, a generalized policy iteration (GPI) algorithm with approximation errors is developed for solving infinite horizon optimal control problems for nonlinear systems. The developed stable GPI algorithm provides a general structure of discrete-time iterative adaptive dynamic programming algorithms, by which most of the discrete-time reinforcement learning algorithms can be described using the GPI structure. It is for the first time that approximation errors are explicitly considered in the GPI algorithm. The properties of the stable GPI algorithm with approximation errors are analyzed. The admissibility of the approximate iterative control law can be guaranteed if the approximation errors satisfy the admissibility criteria. The convergence of the developed algorithm is established, which shows that the iterative value function is convergent to a finite neighborhood of the optimal performance index function, if the approximate errors satisfy the convergence criterion. Finally, numerical examples and comparisons are presented.
关键词	Adaptive Critic Designs Adaptive Dynamic Programming (Adp) Approximate Dynamic Programming Generalized Policy Iteration (Gpi) Neural Networks Neurodynamic Programming Nonlinear Systems Optimal Control Reinforcement Learning
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TNNLS.2017.2661865
关键词[WOS]	DYNAMIC-PROGRAMMING ALGORITHM ; ZERO-SUM GAMES ; NONLINEAR-SYSTEMS ; TRACKING CONTROL ; UNKNOWN DYNAMICS ; VALUE-ITERATION ; CONTROL SCHEME ; REINFORCEMENT ; DESIGN
收录类别	SCI
语种	英语
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:000427859600037
引用统计	被引频次：39[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/173211/13634
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 Chinese Acad Sci, Beijing 100049, Peoples R China 3.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,Li, Benkai,Song, Ruizhuo. Discrete-Time Stable Generalized Self-Learning Optimal Control With Approximation Errors[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(4):1226-1238.
APA	Wei, Qinglai,Li, Benkai,&Song, Ruizhuo.(2018).Discrete-Time Stable Generalized Self-Learning Optimal Control With Approximation Errors.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(4),1226-1238.
MLA	Wei, Qinglai,et al."Discrete-Time Stable Generalized Self-Learning Optimal Control With Approximation Errors".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.4(2018):1226-1238.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
07866891.pdf（2475KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览