Robust value iteration for optimal control of discrete-time linear systems

被引：0

作者：

Lai, Jing ^{[1
]}

Xiong, Junlin ^{[2
]}

机构：

[1] Hefei Univ Technol, Sch Elect Engn & Automat, Hefei 230009, Peoples R China

[2] Univ Sci & Technol China, Dept Automat, Hefei 230026, Peoples R China

来源：

AUTOMATICA | 2025年 / 174卷

基金：

中国国家自然科学基金;

关键词：

Value iteration; Robust analysis; Reinforcement learning; Stochastic systems; ADAPTIVE OPTIMAL-CONTROL; CONE;

D O I：

10.1016/j.automatica.2025.112121

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper investigates properties of value iteration in the presence of deviations, starting from a benchmark control problem for discrete-time linear systems. Using properties of invariant metrics, value iteration for the considered control problem is demonstrated to be robust to small deviations. Specifically, value iteration enjoys a non-asymptotic convergence property when the deviations keep small in the execution, and generates solutions that converge to a small neighborhood of the optimal ones. As an extension, an optimistic model-free value iteration is proposed for systems suffering from additive noise of zero mean with the estimation error analysis and convergence analysis. The proposed results are illustrated through numerical simulations. (c) 2025 Published by Elsevier Ltd.

引用

页数：8

共 50 条

[21] Optimal Self-Learning Control Scheme for Discrete-Time Nonlinear Systems Using Local Value Iteration
Wei, Qinglai
Liu, Derong
2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2016, : 3544 - 3549
[22] On the optimal control of linear discrete-time systems via discrete orthogonal functions
Indian Inst of Technology, Kharagpur, India
J Franklin Inst, 4 (731-738):
[23] On the optimal control of linear discrete-time systems via discrete orthogonal functions
Mohan, BM
Datta, KB
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 1998, 335B (04): : 731 - 738
[24] Robust Optimal Control of Uncertain Discrete-Time Multiagent Systems With Digraphs
Zhang, Zhuo
Shi, Yang
Zhang, Zexu
Zhang, Shouxu
Li, Huiping
Xiao, Bing
Yan, Weisheng
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2023, 53 (02): : 861 - 871
[25] Optimal consensus of a class of discrete-time linear multi-agent systems via value iteration with guaranteed admissibility
Li, Pingchuan
Zou, Wencheng
Guo, Jian
Xiang, Zhengrong
NEUROCOMPUTING, 2023, 516 : 1 - 10
[26] Discrete-time robust control of linear periodically time-varying systems
Kalender, S.
Flashner, H.
PROCEEDINGS OF THE ASME INTERNATIONAL DESIGN ENGINEERING TECHNICAL CONFERENCES AND COMPUTERS AND INFORMATION IN ENGINEERING CONFERENCE 2007, VOL 5, PTS A-C,, 2008, : 881 - 893
[27] Discrete-time robust inverse optimal control for a class of nonlinear systems
CINVESTAV Unidad Guadalajara, Jalisco 45019, Mexico
IFAC Proc. Vol. (IFAC-PapersOnline), 1 PART 1 (8595-8600):
[28] Robust control for uncertain discrete-time jump linear systems with time delay
Cao, YY
Frank, PM
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART I-JOURNAL OF SYSTEMS AND CONTROL ENGINEERING, 1999, 213 (I6) : 477 - 488
[29] Linear Quadratic Optimal Control for Discrete-time Markov Jump Linear Systems
Han, Chunyan
Li, Hongdan
Wang, Wei
Zhang, Huanshui
2018 IEEE 14TH INTERNATIONAL CONFERENCE ON CONTROL AND AUTOMATION (ICCA), 2018, : 769 - 774
[30] Regularization and robust control of uncertain singular discrete-time linear systems
Ibrir, Salim
IMA JOURNAL OF MATHEMATICAL CONTROL AND INFORMATION, 2007, 24 (01) : 71 - 80

← 1 2 3 4 5 →