Finite-Approximation-Error-Based Discrete-Time Iterative Adaptive Dynamic Programming

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	Finite-Approximation-Error-Based Discrete-Time Iterative Adaptive Dynamic Programming
	Wei, Qinglai; Wang, Fei-Yue; Liu, Derong; Yang, Xiong
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
	2014-12-01
卷号	44 期号:12 页码:2820-2833
文章类型	Article
摘要	In this paper, a new iterative adaptive dynamic programming (ADP) algorithm is developed to solve optimal control problems for infinite horizon discrete-time nonlinear systems with finite approximation errors. First, a new generalized value iteration algorithm of ADP is developed to make the iterative performance index function converge to the solution of the Hamilton-Jacobi-Bellman equation. The generalized value iteration algorithm permits an arbitrary positive semi-definite function to initialize it, which overcomes the disadvantage of traditional value iteration algorithms. When the iterative control law and iterative performance index function in each iteration cannot accurately be obtained, for the first time a new "design method of the convergence criteria" for the finite-approximation-error-based generalized value iteration algorithm is established. A suitable approximation error can be designed adaptively to make the iterative performance index function converge to a finite neighborhood of the optimal performance index function. Neural networks are used to implement the iterative ADP algorithm. Finally, two simulation examples are given to illustrate the performance of the developed method.
关键词	Adaptive Critic Designs Adaptive Dynamic Programming (Adp) Approximate Dynamic Programming Approximation Error Neural Networks Neuro-dynamic Programming Nonlinear Systems Optimal Control Reinforcement Learning Value Iteration
WOS标题词	Science & Technology ; Technology
关键词[WOS]	OPTIMAL TRACKING CONTROL ; NONLINEAR-SYSTEMS ; CONTROL SCHEME ; CONTROLLER-DESIGN ; LEARNING CONTROL ; REINFORCEMENT ; ALGORITHM ; OPTIMIZATION ; PERFORMANCE ; CONVERGENCE
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000345629000047
引用统计	被引频次：165[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/173211/3625
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
作者单位	Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, 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,Wang, Fei-Yue,Liu, Derong,et al. Finite-Approximation-Error-Based Discrete-Time Iterative Adaptive Dynamic Programming[J]. IEEE TRANSACTIONS ON CYBERNETICS,2014,44(12):2820-2833.
APA	Wei, Qinglai,Wang, Fei-Yue,Liu, Derong,&Yang, Xiong.(2014).Finite-Approximation-Error-Based Discrete-Time Iterative Adaptive Dynamic Programming.IEEE TRANSACTIONS ON CYBERNETICS,44(12),2820-2833.
MLA	Wei, Qinglai,et al."Finite-Approximation-Error-Based Discrete-Time Iterative Adaptive Dynamic Programming".IEEE TRANSACTIONS ON CYBERNETICS 44.12(2014):2820-2833.

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
Finite-Approximation（1826KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载