Online identifier-actor-critic algorithm for optimal control of nonlinear systems

doi:10.1002/oca.2259

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

	Online identifier-actor-critic algorithm for optimal control of nonlinear systems
	Lin, Hanquan1 ; Wei, Qinglai1 ; Liu, Derong 2
发表期刊	OPTIMAL CONTROL APPLICATIONS & METHODS
	2017-05-01
卷号	38 期号:3 页码:317-335
文章类型	Article
摘要	In this paper, a novel identifier-actor-critic optimal control scheme is developed for discrete-time affine nonlinear systems with uncertainties. In contrast to traditional adaptive dynamic programming methodology, which requires at least partial knowledge of the system dynamics, a neural-network identifier is employed to learn the unknown control coefficient matrix working together with actor-critic-based scheme to solve the optimal control online. The critic network learns the approximate value function at each step. The actor network attempts to improve the current policy based on the approximate value function. The weights of all neural networks are updated at each sampling instant. Lyapunov theory is utilized to prove the stability of closed-loop system. It shows that system states and neural network weights are uniformly ultimately bounded. Finally, simulations are provided to illustrate the effectiveness of the developed method. Copyright (C) 2016 John Wiley & Sons, Ltd.
关键词	Adaptive Dynamic Programming Optimal Control Discrete-time Nonlinear System Neural Network Online Learning Lyapunov Method
WOS标题词	Science & Technology ; Technology ; Physical Sciences
DOI	10.1002/oca.2259
关键词[WOS]	DISCRETE-TIME-SYSTEMS ; OPTIMAL TRACKING CONTROL ; INPUT-OUTPUT DATA ; POLICY ITERATION ; DYNAMICS ; DESIGNS
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61233001 ; Beijing Natural Science Foundation(4132078) ; Early Career Development Award of SKLMCCS ; 61273140 ; 61304086 ; 61374105)
WOS研究方向	Automation & Control Systems ; Operations Research & Management Science ; Mathematics
WOS类目	Automation & Control Systems ; Operations Research & Management Science ; Mathematics, Applied
WOS记录号	WOS:000400964800002
引用统计	被引频次：17[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/173211/15111
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	Lin, Hanquan,Wei, Qinglai,Liu, Derong. Online identifier-actor-critic algorithm for optimal control of nonlinear systems[J]. OPTIMAL CONTROL APPLICATIONS & METHODS,2017,38(3):317-335.
APA	Lin, Hanquan,Wei, Qinglai,&Liu, Derong.(2017).Online identifier-actor-critic algorithm for optimal control of nonlinear systems.OPTIMAL CONTROL APPLICATIONS & METHODS,38(3),317-335.
MLA	Lin, Hanquan,et al."Online identifier-actor-critic algorithm for optimal control of nonlinear systems".OPTIMAL CONTROL APPLICATIONS & METHODS 38.3(2017):317-335.

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
OCA2259.pdf（2888KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载