Model-free algorithm for consensus of discrete-time multi-agent systems using reinforcement learning method

DOI10.1016/j.jfranklin.2023.08.010zbMath1521.93179MaRDI QIDQ6053923

Jin Zhao, Mingkang Long, Hui Luo, Qing An, Housheng Su

Publication date: 27 September 2023

Published in: Journal of the Franklin Institute (Search for Journal in Brave)

zbMATH Keywords

reinforcement learningconsensusdiscrete-time multi-agent systems

Mathematics Subject Classification ID

Discrete-time control/observation systems (93C55) Multi-agent systems (93A16) Consensus (93D50)

Cites Work

• Unnamed Item
• Multi-player non-zero-sum games: online adaptive learning solution of coupled Hamilton-Jacobi equations
• Group controllability of two-time-scale multi-agent networks
• Global Mittag-Leffler consensus for fractional singularly perturbed multi-agent systems with discontinuous inherent dynamics via event-triggered control strategy
• Iterative learning formation control for continuous-time multi-agent systems with randomly varying trial lengths
• Finite-time consensus control for a class of multi-agent systems with dead-zone input
• Deployment of second-order networked mobile agents over a smooth curve
• Multi-agent discrete-time graphical games and reinforcement learning solutions
• Proximal nested primal-dual gradient algorithms for distributed constraint-coupled composite optimization
• Discrete-time dynamic graphical games: model-free reinforcement learning solution
• An iterative Q-learning based global consensus of discrete-time saturated multi-agent systems
• Event-Triggered Real-Time Scheduling of Stabilizing Control Tasks
• Consensus on Directed Matrix-Weighted Networks
• Interval Coordination of Multiagent Networks With Antagonistic Interactions