Online Iterative Adaptive Dynamic Programming Approach for Solving the Zero-Sum Game for Nonlinear Continuous-Time Systems with Partially Unknown Dynamics

被引：1

作者：

Fu, Bin ^{[1
]}

Sun, Bo ^{[2
]}

Guo, Hang ^{[1
]}

Yang, Tao ^{[1
]}

Fu, Wenxing ^{[1
]}

机构：

[1] Northwestern Polytech Univ, Unmanned Syst Res Inst, Xian 710072, Shanxi, Peoples R China

[2] Delft Univ Technol, Fac Aerosp Engn, NL-2629 HS Delft, Netherlands

来源：

PROCEEDINGS OF 2022 INTERNATIONAL CONFERENCE ON AUTONOMOUS UNMANNED SYSTEMS, ICAUS 2022 | 2023年 / 1010卷

关键词：

Approximation dynamic programming; Zero-sum game; Integral reinforcement learning; Online learning; Value iteration; REINFORCEMENT; DESIGN;

D O I：

10.1007/978-981-99-0479-2_262

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The current study presents an online iterative adaptive dynamic programming approach to resolve the zero-sum game (ZSG) for nonlinear continuous-time (CT) systems containing a partially unknown dynamic. The Hamilton-Jacobian-Issacs (HJI) equation is solved along the state trajectory according to the value function approximation and the policy improvement online. Relaxed dynamic programming is utilized to ensure the algorithm's convergence. Model and costate networks were established to conduct the method. Computational simulations are performed to present the efficiency of the algorithm.

引用

页码：2833 / 2842

页数：10

共 50 条

[41] Output Constrained Adaptive Dynamic Programming for Continuous-Time Nonlinear Systems
Yang, Jingjing
Chen, Jingjia
Fan, Bo
Yang, Qinmin
2017 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (SSCI), 2017, : 1292 - 1298
[42] Event-triggered adaptive dynamic programming for multi-player zero-sum games with unknown dynamics
Yongwei Zhang
Bo Zhao
Derong Liu
Soft Computing, 2021, 25 : 2237 - 2251
[43] Event-triggered adaptive dynamic programming for multi-player zero-sum games with unknown dynamics
Zhang, Yongwei
Zhao, Bo
Liu, Derong
SOFT COMPUTING, 2021, 25 (03) : 2237 - 2251
[44] Zero-sum continuous-time Markov pure jump game over a fixed duration
Guo, Xin
Zhang, Yi
JOURNAL OF MATHEMATICAL ANALYSIS AND APPLICATIONS, 2017, 452 (02) : 1194 - 1208
[45] Adaptive optimal safety tracking control for multiplayer mixed zero-sum games of continuous-time systems
Qin, Chunbin
Zhang, Zhongwei
Shang, Ziyang
Zhang, Jishi
Zhang, Dehua
APPLIED INTELLIGENCE, 2023, 53 (14) : 17460 - 17475
[46] Adaptive optimal safety tracking control for multiplayer mixed zero-sum games of continuous-time systems
Chunbin Qin
Zhongwei Zhang
Ziyang Shang
Jishi Zhang
Dehua Zhang
Applied Intelligence, 2023, 53 : 17460 - 17475
[47] Event-triggered distributed zero-sum differential game for nonlinear multi-agent systems using adaptive dynamic programming
Sun, Jingliang
Long, Teng
ISA TRANSACTIONS, 2021, 110 : 39 - 52
[48] Continuous-time ADP for linear systems with partially unknown dynamics
Vrabie, Draguna
Abu-Khalaf, Murad
Lewis, Frank L.
Wang, Youyi
2007 IEEE INTERNATIONAL SYMPOSIUM ON APPROXIMATE DYNAMIC PROGRAMMING AND REINFORCEMENT LEARNING, 2007, : 247 - +
[49] Adaptive Dynamic Programming Algorithm for Finding Online the Equilibrium Solution of the Two-Player Zero-Sum Differential Game
Vrabie, Draguna
Lewis, Frank
2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
[50] Data-Driven Adaptive Dynamic Programming for Optimal Control of Continuous-Time Multicontroller Systems With Unknown Dynamics
Zhao, Jingang
IEEE ACCESS, 2022, 10 : 41503 - 41511

← 1 2 3 4 5 →