Off-policy integral reinforcement learning optimal tracking control for continuous-time chaotic systems

doi:10.1088/1674-1056/24/9/090504

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

	Off-policy integral reinforcement learning optimal tracking control for continuous-time chaotic systems
	Wei Qing-Lai1 ; Song Rui-Zhuo 2; Sun Qiu-Ye 3; Xiao Wen-Dong 2
发表期刊	CHINESE PHYSICS B
	2015-09-01
卷号	24 期号:9
文章类型	Article
摘要	This paper estimates an off-policy integral reinforcement learning (IRL) algorithm to obtain the optimal tracking control of unknown chaotic systems. Off-policy IRL can learn the solution of the HJB equation from the system data generated by an arbitrary control. Moreover, off-policy IRL can be regarded as a direct learning method, which avoids the identification of system dynamics. In this paper, the performance index function is first given based on the system tracking error and control error. For solving the Hamilton-Jacobi-Bellman (HJB) equation, an off-policy IRL algorithm is proposed. It is proven that the iterative control makes the tracking error system asymptotically stable, and the iterative performance index function is convergent. Simulation study demonstrates the effectiveness of the developed tracking control method.
关键词	Adaptive Dynamic Programming Approximate Dynamic Programming Chaotic System Optimal Tracking Control
WOS标题词	Science & Technology ; Physical Sciences
DOI	10.1088/1674-1056/24/9/090504
关键词[WOS]	ATTRACTOR ; DYNAMICS ; DESIGN
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61304079 ; Beijing Natural Science Foundation, China(4132078 ; China Postdoctoral Science Foundation(2013M530527) ; Fundamental Research Funds for the Central Universities, China(FRF-TP-14-119A2) ; Open Research Project from State Key Laboratory of Management and Control for Complex Systems, China(20150104) ; 61374105) ; 4143065)
WOS研究方向	Physics
WOS类目	Physics, Multidisciplinary
WOS记录号	WOS:000363325200021
引用统计	被引频次：8[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/173211/10493
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, Sch Automat & Elect Engn, Beijing 100083, Peoples R China 3.Northeastern Univ, Sch Informat Sci & Engn, Shenyang 110004, 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 Qing-Lai,Song Rui-Zhuo,Sun Qiu-Ye,et al. Off-policy integral reinforcement learning optimal tracking control for continuous-time chaotic systems[J]. CHINESE PHYSICS B,2015,24(9).
APA	Wei Qing-Lai,Song Rui-Zhuo,Sun Qiu-Ye,&Xiao Wen-Dong.(2015).Off-policy integral reinforcement learning optimal tracking control for continuous-time chaotic systems.CHINESE PHYSICS B,24(9).
MLA	Wei Qing-Lai,et al."Off-policy integral reinforcement learning optimal tracking control for continuous-time chaotic systems".CHINESE PHYSICS B 24.9(2015).