Discrete-Time Local Value Iteration Adaptive Dynamic Programming: Admissibility and Termination Analysis

被引：33

作者：

Wei, Qinglai ^{[1
]}

Liu, Derong ^{[2
]}

Lin, Qiao ^{[1
]}

机构：

[1] Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China

[2] Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS | 2017年 / 28卷 / 11期

基金：

中国国家自然科学基金;

关键词：

Adaptive critic designs; adaptive dynamic programming (ADP); approximate dynamic programming; local iteration; neural networks; neurodynamic programming; nonlinear systems; optimal control; OPTIMAL TRACKING CONTROL; ZERO-SUM GAME; NONLINEAR-SYSTEMS; FEEDBACK-CONTROL; CONTROL SCHEME; LEARNING CONTROL; NETWORKS; DESIGN;

D O I：

10.1109/TNNLS.2016.2593743

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, a novel local value iteration adaptive dynamic programming (ADP) algorithm is developed to solve infinite horizon optimal control problems for discrete-time nonlinear systems. The focuses of this paper are to study admissibility properties and the termination criteria of discrete-time local value iteration ADP algorithms. In the discrete-time local value iteration ADP algorithm, the iterative value functions and the iterative control laws are both updated in a given subset of the state space in each iteration, instead of the whole state space. For the first time, admissibility properties of iterative control laws are analyzed for the local value iteration ADP algorithm. New termination criteria are established, which terminate the iterative local ADP algorithm with an admissible approximate optimal control law. Finally, simulation results are given to illustrate the performance of the developed algorithm.

引用

页码：2490 / 2502

页数：13

共 50 条

[31] Discrete-Time Deterministic Q-Learning: A Novel Convergence Analysis
Wei, Qinglai
Lewis, Frank L.
Sun, Qiuye
Yan, Pengfei
Song, Ruizhuo
IEEE TRANSACTIONS ON CYBERNETICS, 2017, 47 (05) : 1224 - 1237
[32] Multi-step heuristic dynamic programming for optimal control of nonlinear discrete-time systems
Luo, Biao
Liu, Derong
Huang, Tingwen
Yang, Xiong
Ma, Hongwen
INFORMATION SCIENCES, 2017, 411 : 66 - 83
[33] Constrained-Cost Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems
Wei, Qinglai
Li, Tao
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2024, 35 (03) : 3251 - 3264
[34] Optimal control of unknown nonaffine nonlinear discrete-time systems based on adaptive dynamic programming
Wang, Ding
Liu, Derong
Wei, Qinglai
Zhao, Dongbin
Jin, Ning
AUTOMATICA, 2012, 48 (08) : 1825 - 1832
[35] Event-triggered adaptive dynamic programming for discrete-time multi-player games
Wang, Ziyang
Wei, Qinglai
Liu, Derong
INFORMATION SCIENCES, 2020, 506 : 457 - 470
[36] Finite-horizon neuro-optimal tracking control for a class of discrete-time nonlinear systems using adaptive dynamic programming approach
Wang, Ding
Liu, Derong
Wei, Qinglai
NEUROCOMPUTING, 2012, 78 (01) : 14 - 22
[37] Dynamic event-triggered control for discrete-time nonlinear Markov jump systems using policy iteration-based adaptive dynamic programming
Tang, Fanghua
Wang, Huanqing
Chang, Xiao-Heng
Zhang, Liang
Alharbi, Khalid H.
NONLINEAR ANALYSIS-HYBRID SYSTEMS, 2023, 49
[38] Discrete-Time Two-Player Zero-Sum Games for Nonlinear Systems Using Iterative Adaptive Dynamic Programming
Wei, Qinglai
Liu, Derong
ADVANCES IN NEURAL NETWORKS - ISNN 2016, 2016, 9719 : 269 - 276
[39] FINITE-HORIZON ε-OPTIMAL TRACKING CONTROL OF DISCRETE-TIME LINEAR SYSTEMS USING ITERATIVE APPROXIMATE DYNAMIC PROGRAMMING
Tan, Fuxiao
Luo, Bin
Guan, Xinping
ASIAN JOURNAL OF CONTROL, 2015, 17 (01) : 176 - 189
[40] A novel policy iteration based deterministic Q-learning for discrete-time nonlinear systems
WEI QingLai
LIU DeRong
ScienceChina(InformationSciences), 2015, 58 (12) : 147 - 161

← 1 2 3 4 5 →