A Machine Learning Method for Stackelberg Mean Field Games
From MaRDI portal
Abstract: In this paper, we propose a single-level numerical approach that uses machine learning techniques to solve bi-level Stackelberg problems between a principal and a mean field of agents. In Stackelberg mean field games, there is an infinite population of agents who play a non-cooperative game and choose their controls to optimize their individual objectives while interacting with the principal and other agents through the population distribution. The principal can influence the mean field game Nash equilibrium at the population level through policies, and she aims at optimizing her own objective, which depends on the population distribution. This leads to a bi-level problem between the principal and mean field of agents that cannot be solved using traditional methods for mean field games. We propose a reformulation of this problem as a single-level mean field optimal control problem through a penalization approach. We prove convergence of the reformulated problem to the original problem. We then propose a numerical method based on neural networks and illustrate it on several examples from the literature.
This page was built for publication: A Machine Learning Method for Stackelberg Mean Field Games
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6427133)
