4 citations · 5 across the 2 of their papers we have counts for
3 papers
math.OC2025
Initialization-driven neural generation and training for high-dimensional optimal control and first-order mean field games
Mouhcine Assouli, Justina Gianatti, Badr Missaoui +1
This paper first introduces a method to approximate the value function of high-dimensional optimal control by neural networks. Based on the established relationship between Pontrya…
math.OC2023★ 1 cited
Deep Policy Iteration for High-Dimensional Mean Field Games
Mouhcine Assouli, Badr Missaoui
This paper introduces Deep Policy Iteration (DPI), a novel approach that integrates the strengths of Neural Networks with the stability and convergence advantages of Policy Iterati…
cs.LG2023★ 4 cited
Deep Learning for Mean Field Games with non-separable Hamiltonians
Mouhcine Assouli, Badr Missaoui
This paper introduces a new method based on Deep Galerkin Methods (DGMs) for solving high-dimensional stochastic Mean Field Games (MFGs). We achieve this by using two neural networ…