%0 Journal Article
%T 基于强化学习的多智能体系统一致性跟踪控制算法<br>Reinforcement Learning-Based Consensus Tracking Control Algorithm for Multi-Agent Systems
%A 刘人志
%J Computer Science and Application
%P 374-381
%@ 2161-881X
%D 2025
%I Hans Publishing
%R 10.12677/csa.2025.154110
%X 本文提出了一种新颖的基于强化学习的无模型自适应控制算法&#65292;适用于具有未知动态的离散时间非线性多智能体系统。采用等效动态线性化算法来设计最优控制器。针对Q学习策略和演员&#8211;评论家(actor-critic)神经网络进行了重构&#65292;以促进一致性控制。所提出的强化学习方法能够仅基于输入&#8211;输出数据实时动态调整线性化参数。通过数值仿真验证了该方法的有效性。<br>This paper presents a novel reinforcement learning-based model-free adaptive control algorithm for discrete-time nonlinear multi-agent systems with unknown dynamics. The equivalent dynamic linearization algorithm is employed to design an optimal controller. The Q-Learning strategy and actor-critic neural network are restructured to facilitate consensus control. The proposed reinforcement learning approach dynamically adjusts linearization parameters in real-time using only input-output data. Numerical simulations validate the method&#8217;s effectiveness.
%K 强化学习&#65292
%K 非线性多智能体系统&#65292
%K 跟踪控制&#65292
%K 动态线性化<br>Reinforcement Learning
%K Nonlinear Multi-Agent System
%K Tracking Control
%K Dynamic Linearization
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=113155