An iterative Q-learning based global consensus of discrete-time saturated multi-agent systems
From MaRDI portal
Publication:4973006
DOI10.1063/1.5120106zbMath1429.93336OpenAlexW2981085430WikidataQ91057949 ScholiaQ91057949MaRDI QIDQ4973006
Housheng Su, Guo-Ping Jiang, Mingkang Long, Xiao Fan Wang, Xiao-Ling Wang
Publication date: 29 November 2019
Published in: Chaos: An Interdisciplinary Journal of Nonlinear Science (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1063/1.5120106
Discrete-time control/observation systems (93C55) Multi-agent systems (93A16) Consensus (93D50) Iterative learning control (93B47)
Related Items
Completely model-free RL-based consensus of continuous-time multi-agent systems ⋮ Model-free algorithm for consensus of discrete-time multi-agent systems using reinforcement learning method
Cites Work
- Appointed-time consensus: accurate and practical designs
- Output synchronization of heterogeneous discrete-time systems: a model-free optimal approach
- Second-order controllability of two-time-scale multi-agent systems
- Consensus of hybrid multi-agent systems by event-triggered/self-triggered strategy
- Containment control of second-order multi-agent systems via intermittent sampled position data communication
- A revisit to block and recursive least squares for parameter estimation
- Swarming behaviors in multi-agent systems with nonlinear dynamics
- Stabilizing Solution and Parameter Dependence of Modified Algebraic Riccati Equation With Application to Discrete-Time Network Synchronization
- Discrete-time dynamic graphical games: model-free reinforcement learning solution
- Adaptive Control Design and Analysis
- Synchronization of multi-agent systems with metric-topological interactions
- Positive Edge-Consensus for Nodal Networks via Output Feedback
- Synchronization of stochastic hybrid oscillators driven by a common switching environment
- Semi-Global Leader-Following Consensus of Linear Multi-Agent Systems With Input Saturation via Low Gain Feedback
- An iterative Q‐learning scheme for the global stabilization of discrete‐time linear systems subject to actuator saturation
- Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers
- Controllability of heterogeneous multiagent systems with two-time-scale feature
