Policy Gradient Adaptive Dynamic Programming for Data-Based Optimal Control

doi:10.1109/TCYB.2016.2623859

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

	Policy Gradient Adaptive Dynamic Programming for Data-Based Optimal Control
	Luo, Biao1 ; Liu, Derong 2; Wu, Huai-Ning 3; Wang, Ding1 ; Lewis, Frank L.4,5
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
	2017-10-01
卷号	47 期号:10 页码:3341-3354
文章类型	Article
摘要	The model-free optimal control problem of general discrete-time nonlinear systems is considered in this paper, and a data-based policy gradient adaptive dynamic programming (PGADP) algorithm is developed to design an adaptive optimal controller method. By using offline and online data rather than the mathematical system model, the PGADP algorithm improves control policy with a gradient descent scheme. The convergence of the PGADP algorithm is proved by demonstrating that the constructed Q-function sequence converges to the optimal Q-function. Based on the PGADP algorithm, the adaptive control method is developed with an actor-critic structure and the method of weighted residuals. Its convergence properties are analyzed, where the approximate Q-function converges to its optimum. Computer simulation results demonstrate the effectiveness of the PGADP-based adaptive control method.
关键词	Adaptive Control Adaptive Dynamic Programming (Adp) Data-based Off-policy Learning Optimal Control Policy Gradient
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCYB.2016.2623859
关键词[WOS]	DISCRETE-TIME-SYSTEMS ; H-INFINITY CONTROL ; SPATIALLY DISTRIBUTED PROCESSES ; AFFINE NONLINEAR-SYSTEMS ; OPTIMAL TRACKING CONTROL ; HORIZON OPTIMAL-CONTROL ; ZERO-SUM GAMES ; UNKNOWN DYNAMICS ; CONTROL DESIGN ; LINEAR-SYSTEMS
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61233001 ; 61273140 ; 61304086 ; 61374105 ; 61503377 ; 61533017 ; 61473011 ; U1501251)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000409311800032
引用统计	被引频次：145[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/173211/12527
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	Luo, Biao
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 3.Beihang Univ, Sci & Technol Aircraft Control Lab, Beijing 100191, Peoples R China 4.Univ Texas Arlington, Res Inst, Ft Worth, TX 76118 USA 5.Northeastern Univ, State Key Lab Synthet Automat Proc Ind, Shenyang 110819, Liaoning, Peoples R China
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Luo, Biao,Liu, Derong,Wu, Huai-Ning,et al. Policy Gradient Adaptive Dynamic Programming for Data-Based Optimal Control[J]. IEEE TRANSACTIONS ON CYBERNETICS,2017,47(10):3341-3354.
APA	Luo, Biao,Liu, Derong,Wu, Huai-Ning,Wang, Ding,&Lewis, Frank L..(2017).Policy Gradient Adaptive Dynamic Programming for Data-Based Optimal Control.IEEE TRANSACTIONS ON CYBERNETICS,47(10),3341-3354.
MLA	Luo, Biao,et al."Policy Gradient Adaptive Dynamic Programming for Data-Based Optimal Control".IEEE TRANSACTIONS ON CYBERNETICS 47.10(2017):3341-3354.

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
TCyb 2016.pdf（3217KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载