Invariant Adaptive Dynamic Programming for Discrete-Time Optimal Control

doi:10.1109/TSMC.2019.2911900

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 深度强化学习

	Invariant Adaptive Dynamic Programming for Discrete-Time Optimal Control
	Zhu, Yuanheng1,2 ; Zhao, Dongbin1,2 ; He, Haibo 3
发表期刊	IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
ISSN	2168-2216
	2020-11-01
卷号	50 期号:11 页码:3959-3971
通讯作者	He, Haibo(he@ele.uri.edu)
摘要	For systems that can only be locally stabilized, control laws and their effective regions are both important. In this paper, invariant policy iteration is proposed to solve the optimal control of discrete-time systems. At each iteration, a given policy is evaluated in its invariantly admissible region, and a new policy and a new region are updated for the next iteration. Theoretical analysis shows the method is regionally convergent to the optimal value and the optimal policy. Combined with sum-of-squares polynomials, the method is able to achieve the near-optimal control of a class of discrete-time systems. An invariant adaptive dynamic programming algorithm is developed to extend the method to scenarios where system dynamics is not available. Online data are utilized to learn the near-optimal policy and the invariantly admissible region. Simulated experiments verify the effectiveness of our method.
关键词	Optimal control Discrete-time systems Heuristic algorithms Dynamic programming Convergence Artificial intelligence Nonlinear systems Adaptive dynamic programming discrete-time systems invariant admissibility optimal control policy iteration sum of squares
DOI	10.1109/TSMC.2019.2911900
关键词[WOS]	NONLINEAR-SYSTEMS ; POLICY ITERATION ; STABILITY ; SUM
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61603382]
项目资助者	National Natural Science Foundation of China
WOS研究方向	Automation & Control Systems ; Computer Science
WOS类目	Automation & Control Systems ; Computer Science, Cybernetics
WOS记录号	WOS:000578826300003
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	强化与进化学习
引用统计	被引频次：27[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/173211/42180
专题	多模态人工智能系统全国重点实验室_深度强化学习
通讯作者	He, Haibo
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 3.Univ Rhode Isl, Dept Elect Comp & Biomed Engn, Kingston, RI 02881 USA
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	Zhu, Yuanheng,Zhao, Dongbin,He, Haibo. Invariant Adaptive Dynamic Programming for Discrete-Time Optimal Control[J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,2020,50(11):3959-3971.
APA	Zhu, Yuanheng,Zhao, Dongbin,&He, Haibo.(2020).Invariant Adaptive Dynamic Programming for Discrete-Time Optimal Control.IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,50(11),3959-3971.
MLA	Zhu, Yuanheng,et al."Invariant Adaptive Dynamic Programming for Discrete-Time Optimal Control".IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS 50.11(2020):3959-3971.