Integral Reinforcement Learning-Based Online Adaptive Dynamic Event-Triggered Control Design in Mixed Zero-Sum Games for Unknown Nonlinear Systems

Mixed zero-sum games consider both zero-sum and non-zero-sum differential game problems simultaneously. In this paper, multiplayer mixed zero-sum games (MZSGs) are studied by the means of an integral reinforcement learning (IRL) algorithm under the dynamic event-triggered control (DETC) mechanism fo...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuling Liang, Zhi Shao, Hanguang Su, Lei Liu, Xiao Mao
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Mathematics
Subjects:
Online Access:https://www.mdpi.com/2227-7390/12/24/3916
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846103779851632640
author Yuling Liang
Zhi Shao
Hanguang Su
Lei Liu
Xiao Mao
author_facet Yuling Liang
Zhi Shao
Hanguang Su
Lei Liu
Xiao Mao
author_sort Yuling Liang
collection DOAJ
description Mixed zero-sum games consider both zero-sum and non-zero-sum differential game problems simultaneously. In this paper, multiplayer mixed zero-sum games (MZSGs) are studied by the means of an integral reinforcement learning (IRL) algorithm under the dynamic event-triggered control (DETC) mechanism for completely unknown nonlinear systems. Firstly, the adaptive dynamic programming (ADP)-based on-policy approach is proposed for solving the MZSG problem for the nonlinear system with multiple players. Secondly, to avoid using dynamic information of the system, a model-free control strategy is developed by utilizing actor–critic neural networks (NNs) for addressing the MZSG problem of unknown systems. On this basis, for the purpose of avoiding wasted communication and computing resources, the dynamic event-triggered mechanism is integrated into the integral reinforcement learning algorithm, in which a dynamic triggering condition is designed to further reduce triggering times. With the help of the Lyapunov stability theorem, the system states and weight values of NNs are proven to be uniformly ultimately bounded (UUB) stable. Finally, two examples are demonstrated to show the effectiveness and feasibility of the developed control method. Compared with static event-triggering mode, the simulation results show that the number of actuator updates in the DETC mechanism has been reduced by 55% and 69%, respectively.
format Article
id doaj-art-4d54ccada8da4aa4af8a8014dc4081c4
institution Kabale University
issn 2227-7390
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Mathematics
spelling doaj-art-4d54ccada8da4aa4af8a8014dc4081c42024-12-27T14:38:00ZengMDPI AGMathematics2227-73902024-12-011224391610.3390/math12243916Integral Reinforcement Learning-Based Online Adaptive Dynamic Event-Triggered Control Design in Mixed Zero-Sum Games for Unknown Nonlinear SystemsYuling Liang0Zhi Shao1Hanguang Su2Lei Liu3Xiao Mao4School of Artificial Intelligence, Shenyang University of Technology, Shenyang 110870, ChinaSchool of Artificial Intelligence, Shenyang University of Technology, Shenyang 110870, ChinaSchool of Information Science and Engineer, Northeastern University, Shenyang 110819, ChinaSchool of Science, Liaoning University of Technology, Jinzhou 121000, ChinaSchool of Artificial Intelligence, Shenyang University of Technology, Shenyang 110870, ChinaMixed zero-sum games consider both zero-sum and non-zero-sum differential game problems simultaneously. In this paper, multiplayer mixed zero-sum games (MZSGs) are studied by the means of an integral reinforcement learning (IRL) algorithm under the dynamic event-triggered control (DETC) mechanism for completely unknown nonlinear systems. Firstly, the adaptive dynamic programming (ADP)-based on-policy approach is proposed for solving the MZSG problem for the nonlinear system with multiple players. Secondly, to avoid using dynamic information of the system, a model-free control strategy is developed by utilizing actor–critic neural networks (NNs) for addressing the MZSG problem of unknown systems. On this basis, for the purpose of avoiding wasted communication and computing resources, the dynamic event-triggered mechanism is integrated into the integral reinforcement learning algorithm, in which a dynamic triggering condition is designed to further reduce triggering times. With the help of the Lyapunov stability theorem, the system states and weight values of NNs are proven to be uniformly ultimately bounded (UUB) stable. Finally, two examples are demonstrated to show the effectiveness and feasibility of the developed control method. Compared with static event-triggering mode, the simulation results show that the number of actuator updates in the DETC mechanism has been reduced by 55% and 69%, respectively.https://www.mdpi.com/2227-7390/12/24/3916dynamic event-triggered controlintegral reinforcement learningadaptive dynamic programmingadaptive critic designmixed zero-sum games
spellingShingle Yuling Liang
Zhi Shao
Hanguang Su
Lei Liu
Xiao Mao
Integral Reinforcement Learning-Based Online Adaptive Dynamic Event-Triggered Control Design in Mixed Zero-Sum Games for Unknown Nonlinear Systems
Mathematics
dynamic event-triggered control
integral reinforcement learning
adaptive dynamic programming
adaptive critic design
mixed zero-sum games
title Integral Reinforcement Learning-Based Online Adaptive Dynamic Event-Triggered Control Design in Mixed Zero-Sum Games for Unknown Nonlinear Systems
title_full Integral Reinforcement Learning-Based Online Adaptive Dynamic Event-Triggered Control Design in Mixed Zero-Sum Games for Unknown Nonlinear Systems
title_fullStr Integral Reinforcement Learning-Based Online Adaptive Dynamic Event-Triggered Control Design in Mixed Zero-Sum Games for Unknown Nonlinear Systems
title_full_unstemmed Integral Reinforcement Learning-Based Online Adaptive Dynamic Event-Triggered Control Design in Mixed Zero-Sum Games for Unknown Nonlinear Systems
title_short Integral Reinforcement Learning-Based Online Adaptive Dynamic Event-Triggered Control Design in Mixed Zero-Sum Games for Unknown Nonlinear Systems
title_sort integral reinforcement learning based online adaptive dynamic event triggered control design in mixed zero sum games for unknown nonlinear systems
topic dynamic event-triggered control
integral reinforcement learning
adaptive dynamic programming
adaptive critic design
mixed zero-sum games
url https://www.mdpi.com/2227-7390/12/24/3916
work_keys_str_mv AT yulingliang integralreinforcementlearningbasedonlineadaptivedynamiceventtriggeredcontroldesigninmixedzerosumgamesforunknownnonlinearsystems
AT zhishao integralreinforcementlearningbasedonlineadaptivedynamiceventtriggeredcontroldesigninmixedzerosumgamesforunknownnonlinearsystems
AT hanguangsu integralreinforcementlearningbasedonlineadaptivedynamiceventtriggeredcontroldesigninmixedzerosumgamesforunknownnonlinearsystems
AT leiliu integralreinforcementlearningbasedonlineadaptivedynamiceventtriggeredcontroldesigninmixedzerosumgamesforunknownnonlinearsystems
AT xiaomao integralreinforcementlearningbasedonlineadaptivedynamiceventtriggeredcontroldesigninmixedzerosumgamesforunknownnonlinearsystems