5 papers
Nonlocal Mean Field Schrödinger Bridge with Learned Interactions
Daisuke Inoue, Dante Kalise, Mathieu Laurière
The Schrödinger Bridge Problem connects an initial distribution to a terminal one along a minimum-energy stochastic process. Its mean-field extension, the Mean-Field Schrödinger…
Inverse Problems for Costs and Controls in LQG MFGs via Mean Field Trajectories
Grégoire Lambrecht, Mathieu Laurière
This paper investigates inverse problems for Linear-Quadratic-Gaussian (LQG) Mean Field Games (MFGs) based entirely on the observation of mean-covariance trajectories. We address t…
Particle Methods with Deep Learning for Stochastic Control under Partial Observation
Mathieu Laurière, Xiaolu Tan, Jiefei Yang
Numerical computation of stochastic control problems under partial observation is challenging because the dynamic programming formulation is naturally posed on the conditional dist…
Operator Learning for Families of Finite-State Mean-Field Games
William Hofgard, Asaf Cohen, Mathieu Laurière
Finite-state mean-field games (MFGs) arise as limits of large interacting particle systems and are governed by an MFG system, a coupled forward-backward differential equation consi…
Deep Backward and Galerkin Methods for the Finite State Master Equation
Asaf Cohen, Mathieu Laurière, Ethan Zell
This paper proposes and analyzes two neural network methods to solve the master equation for finite-state mean field games (MFGs). Solving MFGs provides approximate Nash equilibria…