Modified λ-Policy Iteration Based Adaptive Dynamic Programming for Unknown Discrete-Time Linear Systems

被引：6
|
作者：
Jiang, Huaiyuan [1 ]
Zhou, Bin [1 ]
Duan, Guang-Ren [1 ]
机构：
[1] Harbin Inst Technol, Ctr Control Theory & Guidance Technol, Harbin 150001, Peoples R China
来源：
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | 2024年 / 35卷 / 03期
基金：
中国国家自然科学基金;
关键词：
Adaptive dynamic programming (ADP); data-driven control; discrete-time systems; modified 1-policy iteration (1-PI); policy iteration; unknown systems; STABILIZATION;
D O I：
10.1109/TNNLS.2023.3244934
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
this article, the 1-policy iteration (1-PI) method for the optimal control problem of discrete-time linear systems is reconsidered and restated from a novel aspect. First, the traditional 1-PI method is recalled, and some new properties of the traditional 1-PI are proposed. Based on these new properties, a modified 1-PI algorithm is introduced with its convergence proven. Compared with the existing results, the initial con-dition is further relaxed. The data-driven implementation is then constructed with a new matrix rank condition for veri-fying the feasibility of the proposed data-driven implementation. A simulation example verifies the effectiveness of the proposed method.
引用
收藏
页码：3291 / 3301
页数：11
相关论文
共 50 条
  • [31] Bias-Policy Iteration Based Adaptive Dynamic Programming for Linear Fully Actuated Systems
    Jiang, Huaiyuan
    Yang, Xuefei
    Xu, Chuanchuan
    Zhang, Kangkang
    2024 3RD CONFERENCE ON FULLY ACTUATED SYSTEM THEORY AND APPLICATIONS, FASTA 2024, 2024, : 1140 - 1145
  • [32] Optimal Control for Unknown Discrete-Time Nonlinear Markov Jump Systems Using Adaptive Dynamic Programming
    Zhong, Xiangnan
    He, Haibo
    Zhang, Huaguang
    Wang, Zhanshan
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2014, 25 (12) : 2141 - 2155
  • [33] H∞ Control of Unknown Discrete-Time Nonlinear Systems with Control Constraints Using Adaptive Dynamic Programming
    Liu, Derong
    Li, Hongliang
    Wang, Ding
    2012 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2012,
  • [34] Adaptive Optimal Control for Discrete-Time Linear Systems via Hybrid Iteration
    Qasem, Omar
    Gao, Weinan
    Gutierrez, Hector
    2023 IEEE 12TH DATA DRIVEN CONTROL AND LEARNING SYSTEMS CONFERENCE, DDCLS, 2023, : 1141 - 1146
  • [35] Policy gradient adaptive dynamic programming for nonlinear discrete-time zero-sum games with unknown dynamics
    Lin, Mingduo
    Zhao, Bo
    Liu, Derong
    SOFT COMPUTING, 2023, 27 (09) : 5781 - 5795
  • [36] Policy gradient adaptive dynamic programming for nonlinear discrete-time zero-sum games with unknown dynamics
    Mingduo Lin
    Bo Zhao
    Derong Liu
    Soft Computing, 2023, 27 : 5781 - 5795
  • [37] Discrete-Time Impulsive Adaptive Dynamic Programming
    Wei, Qinglai
    Song, Ruizhuo
    Liao, Zehua
    Li, Benkai
    Lewis, Frank L.
    IEEE TRANSACTIONS ON CYBERNETICS, 2020, 50 (10) : 4293 - 4306
  • [38] Neural-network-based stochastic linear quadratic optimal tracking control scheme for unknown discrete-time systems using adaptive dynamic programming
    Xin Chen
    Fang Wang
    Control Theory and Technology, 2021, 19 : 315 - 327
  • [39] Neural-network-based stochastic linear quadratic optimal tracking control scheme for unknown discrete-time systems using adaptive dynamic programming
    Chen, Xin
    Wang, Fang
    CONTROL THEORY AND TECHNOLOGY, 2021, 19 (03) : 315 - 327
  • [40] Spiking Adaptive Dynamic Programming Based on Poisson Process for Discrete-Time Nonlinear Systems
    Wei, Qinglai
    Han, Liyuan
    Zhang, Tielin
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 33 (05) : 1846 - 1856
12345