Adaptive Multi-Step Evaluation Design With Stability Guarantee for Discrete-Time Optimal Learning Control

doi:10.1109/JAS.2023.123684

CASIA OpenIR > 学术期刊 > IEEE/CAA Journal of Automatica Sinica

	Adaptive Multi-Step Evaluation Design With Stability Guarantee for Discrete-Time Optimal Learning Control
	Ding Wang; Jiangyu Wang; Mingming Zhao; Peng Xin; Junfei Qiao
发表期刊	IEEE/CAA Journal of Automatica Sinica
ISSN	2329-9266
	2023
卷号	10 期号:9 页码:1797-1809
摘要	This paper is concerned with a novel integrated multi-step heuristic dynamic programming (MsHDP) algorithm for solving optimal control problems. It is shown that, initialized by the zero cost function, MsHDP can converge to the optimal solution of the Hamilton-Jacobi-Bellman (HJB) equation. Then, the stability of the system is analyzed using control policies generated by MsHDP. Also, a general stability criterion is designed to determine the admissibility of the current control policy. That is, the criterion is applicable not only to traditional value iteration and policy iteration but also to MsHDP. Further, based on the convergence and the stability criterion, the integrated MsHDP algorithm using immature control policies is developed to accelerate learning efficiency greatly. Besides, actor-critic is utilized to implement the integrated MsHDP scheme, where neural networks are used to evaluate and improve the iterative policy as the parameter architecture. Finally, two simulation examples are given to demonstrate that the learning effectiveness of the integrated MsHDP scheme surpasses those of other fixed or integrated methods.
关键词	Adaptive critic artificial neural networks Hamilton-Jacobi-Bellman (HJB) equation multi-step heuristic dynamic programming multi-step reinforcement learning optimal control
DOI	10.1109/JAS.2023.123684
引用统计	被引频次：23[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/173211/52369
专题	学术期刊_IEEE/CAA Journal of Automatica Sinica
推荐引用方式 GB/T 7714	Ding Wang,Jiangyu Wang,Mingming Zhao,et al. Adaptive Multi-Step Evaluation Design With Stability Guarantee for Discrete-Time Optimal Learning Control[J]. IEEE/CAA Journal of Automatica Sinica,2023,10(9):1797-1809.
APA	Ding Wang,Jiangyu Wang,Mingming Zhao,Peng Xin,&Junfei Qiao.(2023).Adaptive Multi-Step Evaluation Design With Stability Guarantee for Discrete-Time Optimal Learning Control.IEEE/CAA Journal of Automatica Sinica,10(9),1797-1809.
MLA	Ding Wang,et al."Adaptive Multi-Step Evaluation Design With Stability Guarantee for Discrete-Time Optimal Learning Control".IEEE/CAA Journal of Automatica Sinica 10.9(2023):1797-1809.

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
JAS-2023-0323.pdf（5140KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载