Exploration noise for learning linear-quadratic mean field games
arXiv:2107.00839
Abstract
The goal of this paper is to demonstrate that common noise may serve as an exploration noise for learning the solution of a mean field game. This concept is here exemplified through a toy linear-quadratic model, for which a suitable form of common noise has already been proven to restore existence and uniqueness. We here go one step further and prove that the same form of common noise may force the convergence of the learning algorithm called `fictitious play', and this without any further potential or monotone structure. Several numerical examples are provided in order to support our theoretical analysis.
References in corpus (12)
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- A regression-based Monte Carlo method to solve backward stochastic differential equations
- A probabilistic weak formulation of mean field games and applications
- A forward--backward stochastic algorithm for quasi-linear PDEs
- Finite mean field games: fictitious play and convergence to a first order continuous mean field game
- A Game-Theoretic Framework for Autonomous Vehicles Velocity Control: Bridging Microscopic Differential Games and Macroscopic Mean Field Games
- Model-Free Mean-Field Reinforcement Learning: Mean-Field MDP and Mean-Field Q-Learning
- Linear-Quadratic Mean-Field Reinforcement Learning: Convergence of Policy Gradient Methods
- A cubature based algorithm to solve decoupled McKean-Vlasov Forward Backward Stochastic Differential Equations
- Entropy Regularization for Mean Field Games with Learning
- Learning in anonymous nonatomic games with applications to first-order mean field games
- Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint