Stability Analysis of Optimal Adaptive Control Using Value Iteration With Approximation Errors

被引：50
|
作者：
Heydari, Ali [1 ]
机构：
[1] Southern Methodist Univ, Dept Mech Engn, Dallas, TX 75205 USA
来源：
IEEE TRANSACTIONS ON AUTOMATIC CONTROL | 2018年 / 63卷 / 09期
基金：
美国国家科学基金会;
关键词：
Adaptive dynamic programming; approximation error; stability analysis; value iteration; TIME NONLINEAR-SYSTEMS; CONVERGENCE;
D O I：
10.1109/TAC.2018.2790260
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Effects of the presence of approximation errors are analyzed on the stability of adaptive optimal control using value iteration, initiated from a stabilizing control policy. This analysis includes the system operated using any single/constant resulting control policy and also using an evolving/time-varying control policy. Sufficient conditions on the 'per iteration' approximation errors are obtained for guaranteeing the stability. A feature of the presented results is providing estimations of the region of attraction, under the approximation errors, so that if the initial condition is within this region, the whole trajectory will remain inside the training region, and hence, the function approximation results remain reliable.
引用
收藏
页码：3119 / 3126
页数：8
相关论文
共 50 条
  • [31] Adaptive control design using stability analysis and tracking errors dynamics for nonlinear square MIMO systems
    Atig, Asma
    Druaux, Fabrice
    Lefebvre, Dimitri
    Abderrahim, Kamel
    Ben Abdennour, Ridha
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2012, 25 (07) : 1450 - 1459
  • [32] Modified value-function-approximation for synchronous policy iteration with single-critic configuration for nonlinear optimal control
    Tang, Difan
    Chen, Lei
    Tian, Zhao Feng
    Hu, Eric
    INTERNATIONAL JOURNAL OF CONTROL, 2021, 94 (05) : 1321 - 1333
  • [33] Policy iteration optimal tracking control for chaotic systems by using an adaptive dynamic programming approach
    魏庆来
    刘德荣
    徐延才
    Chinese Physics B, 2015, 24 (03) : 91 - 98
  • [34] Learning-based adaptive optimal control of linear time-delay systems: A value iteration approach
    Cui, Leilei
    Pang, Bo
    Krstic, Miroslav
    Jiang, Zhong-Ping
    AUTOMATICA, 2025, 171
  • [35] Policy iteration optimal tracking control for chaotic systems by using an adaptive dynamic programming approach
    Wei Qing-Lai
    Liu De-Rong
    Xu Yan-Cai
    CHINESE PHYSICS B, 2015, 24 (03)
  • [36] Boundary Optimal Control for Parabolic Distributed Parameter Systems With Value Iteration
    Sun, Jingyi
    Luo, Biao
    Xu, Xiaodong
    Yang, Chunhua
    IEEE TRANSACTIONS ON CYBERNETICS, 2024, 54 (03) : 1571 - 1581
  • [37] General multi-step value iteration for optimal learning control
    Wang, Ding
    Wang, Jiangyu
    Liu, Derong
    Qiao, Junfei
    AUTOMATICA, 2025, 175
  • [38] An accelerated value/policy iteration scheme for optimal control problems and games
    Alla, Alessandro
    Falcone, Maurizio
    Kalise, Dante
    Lecture Notes in Computational Science and Engineering, 2015, 103 : 489 - 497
  • [39] Stochastic Drift Counteraction Optimal Control and Enhancing Convergence of Value Iteration
    Zidek, Robert A. E.
    Kolmanovsky, Ilya V.
    2016 IEEE 55TH CONFERENCE ON DECISION AND CONTROL (CDC), 2016, : 1119 - 1124
  • [40] Convergence and stability analysis of value iteration Q-learning under non-discounted cost for discrete-time optimal control
    Song, Shijie
    Zhao, Mingming
    Gong, Dawei
    Zhu, Minglei
    NEUROCOMPUTING, 2024, 606
12345