Sparse online kernelized actor-critic Learning in reproducing kernel Hilbert space

doi:10.1007/s10462-021-10045-9

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 深度强化学习

	Sparse online kernelized actor-critic Learning in reproducing kernel Hilbert space
	Yang, Yongliang 1; Zhu, Hufei 1; Zhang, Qichao 2,3; Zhao, Bo 4; Li, Zhenning 5; Wunsch, Donald C.6
刊名	ARTIFICIAL INTELLIGENCE REVIEW
	2021-08-07
页码	36
关键词	Reproducing kernel Hilbert space Actor-critic learning Value function approximation Online sparsification Non-parametric learning
ISSN号	0269-2821
DOI	10.1007/s10462-021-10045-9
通讯作者	Zhao, Bo(zhaobo@bnu.edu.cn)
英文摘要	In this paper, we develop a novel non-parametric online actor-critic reinforcement learning (RL) algorithm to solve optimal regulation problems for a class of continuous-time affine nonlinear dynamical systems. To deal with the value function approximation (VFA) with inherent nonlinear and unknown structure, a reproducing kernel Hilbert space (RKHS)-based kernelized method is designed through online sparsification, where the dictionary size is fixed and consists of updated elements. In addition, the linear independence check condition, i.e., an online criteria, is designed to determine whether the online data should be inserted into the dictionary. The RHKS-based kernelized VFA has a variable structure in accordance with the online data collection, which is different from classical parametric VFA methods with a fixed structure. Furthermore, we develop a sparse online kernelized actor-critic learning RL method to learn the unknown optimal value function and the optimal control policy in an adaptive fashion. The convergence of the presented kernelized actor-critic learning method to the optimum is provided. The boundedness of the closed-loop signals during the online learning phase can be guaranteed. Finally, a simulation example is conducted to demonstrate the effectiveness of the presented kernelized actor-critic learning algorithm.
资助项目	National Natural Science Foundation of China[61903028] ; National Natural Science Foundation of China[61973330] ; National Natural Science Foundation of China[61803371] ; National Natural Science Foundation of China[61773075] ; Beijing Natural Science Foundation[4212038] ; Open Research Project of the State Key Laboratory of Management and Control for Complex Systems, Institute of Sciences[20210108] ; Open Research Project of the State Key Laboratory of Industrial Control Technology, Zhejiang University, China[ICT2021B48] ; Fundamental Research Funds for the Central Universities[2019NTST25] ; State Key Laboratory of Synthetical Automation for Process Industries[2019-KF-23-03]
WOS关键词	FAULT-TOLERANT CONTROL ; NONLINEAR-SYSTEMS ; TRACKING CONTROL ; APPROXIMATION
WOS研究方向	Computer Science
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000682662600001
资助机构	National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Open Research Project of the State Key Laboratory of Management and Control for Complex Systems, Institute of Sciences ; Open Research Project of the State Key Laboratory of Industrial Control Technology, Zhejiang University, China ; Fundamental Research Funds for the Central Universities ; State Key Laboratory of Synthetical Automation for Process Industries
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/45682]
专题	复杂系统管理与控制国家重点实验室_深度强化学习
通讯作者	Zhao, Bo
作者单位	1.Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing, Peoples R China 4.Beijing Normal Univ, Sch Syst Sci, Beijing 100875, Peoples R China 5.Univ Macau, State Key Lab Internet Things Smart City, Taipa 59193, Macao, Peoples R China 6.Missouri Univ Sci & Technol, Dept Elect & Comp Engn, Rolla, MO 65401 USA
推荐引用方式 GB/T 7714	Yang, Yongliang,Zhu, Hufei,Zhang, Qichao,et al. Sparse online kernelized actor-critic Learning in reproducing kernel Hilbert space[J]. ARTIFICIAL INTELLIGENCE REVIEW,2021:36.
APA	Yang, Yongliang,Zhu, Hufei,Zhang, Qichao,Zhao, Bo,Li, Zhenning,&Wunsch, Donald C..(2021).Sparse online kernelized actor-critic Learning in reproducing kernel Hilbert space.ARTIFICIAL INTELLIGENCE REVIEW,36.
MLA	Yang, Yongliang,et al."Sparse online kernelized actor-critic Learning in reproducing kernel Hilbert space".ARTIFICIAL INTELLIGENCE REVIEW (2021):36.