论文标题
用于控制多代理系统的模型预测平均现场游戏
Model Predictive Mean Field Games for Controlling Multi-Agent Systems
论文作者
论文摘要
在控制多代理系统时，性能和可伸缩性之间的权衡是一个主要挑战。在这里，我们通过使用平均现场游戏（MFG）来解决这一困难，该框架可以推论宏观动力学，描述了从其显微镜动力学中描述代理的密度曲线。为了有效地使用MFG，我们提出了一个模型预测MFG（MP-MFG），该模型通过使用内核密度估计来估计试剂群体密度曲线，并通过模型预测性控制来管理输入生成。提出的MP-MFG通过在每个时间步骤监视试剂总体来生成控制输入，从而比常规MFG获得更高的鲁棒性。数值结果表明，当代理模型具有建模误差或系统中的代理数量时，MP-MFG胜过MFG。
When controlling multi-agent systems, the trade-off between performance and scalability is a major challenge. Here, we address this difficulty by using mean field games (MFGs), which is a framework that deduces the macroscopic dynamics describing the density profile of agents from their microscopic dynamics. To effectively use the MFG, we propose a model predictive MFG (MP-MFG), which estimates the agent population density profile with using kernel density estimation and manages the input generation with model predictive control. The proposed MP-MFG generates control inputs by monitoring the agent population at each time step, and thus achieves higher robustness than the conventional MFG. Numerical results show that the MP-MFG outperforms the MFG when the agent model has modeling errors or the number of agents in the system is small.
