Inverse Reinforcement Learning for Disturbance Rejection in Multiagent Systems
- 9 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (11) , 24057-24069
Abstract
This article proposes inverse reinforcement learning (IRL) algorithms to solve the optimal synchronization problems for multiagent systems (MASs) subject to disturbances. A framework of expert–learner MASs is developed to reconstruct the unknown cost functions of the expert MAS. Within this framework, the learner MAS imitates the behavior trajectories of expert MAS under observation. We first present a model-based IRL algorithm including two iteration loops: an inner loop on optimal control and an outer loop on inverse optimal control (IOC). Moreover, a model-free IRL algorithm is further proposed using the observed input and state data without requiring the dynamics knowledge of the two MASs. Then, generalized fuzzy hyperbolic models (GFHMs) are utilized to implement the model-free algorithm, and we provide the convergence and stabilization proofs of our proposed algorithms. Finally, the effectiveness of the proposed algorithms is verified through a simulation example.Keywords
Funding Information
- National Natural Science Foundation of China (62573238)
- Basic Research Program of Jiangsu Province (BK20241889)
- Natural Science Foundation of Nanjing University of Posts and Telecommunications (NY223080)
- Natural Science Foundation of Nanjing University of Posts and Telecommunications (NY224174)
This publication has 28 references indexed in Scilit:
- Dynamic Event-Triggered Optimized Backstepping Containment Control of a Class of Stochastic Nonlinear MASs Using Reinforcement LearningIEEE Internet of Things Journal, 2025
- Potential-Game-Driven Formation Control of AUVs: An Inverse-Reinforcement-Learning-Based SolutionIEEE Journal of Oceanic Engineering, 2025
- Integral and Inverse Reinforcement Learning for Optimal Control Systems and Games2024
- A survey of inverse reinforcement learningArtificial Intelligence Review, 2022
- Online inverse reinforcement learning for nonlinear systems with adversarial attacksInternational Journal of Robust and Nonlinear Control, 2021
- Relay manoeuvre based fixed-time synchronized tracking control for UAV transport systemAerospace Science and Technology, 2020
- Multi-agent zero-sum differential graphical games for disturbance rejection in distributed controlAutomatica, 2016
- Multi-agent differential graphical games: Online adaptive learning solution for synchronization with optimalityAutomatica, 2012
- Optimal Control2012
- Adaptive optimal control for continuous-time linear systems based on policy iterationAutomatica, 2009