A machine learning framework for solving high-dimensional mean field game and mean field control problems
Mean field games (MFG) and mean field control (MFC) are critical classes of multiagent
models for the efficient analysis of massive populations of interacting agents. Their areas of …
models for the efficient analysis of massive populations of interacting agents. Their areas of …
Ot-flow: Fast and accurate continuous normalizing flows via optimal transport
A normalizing flow is an invertible mapping between an arbitrary probability distribution and
a standard normal distribution; it can be used for density estimation and statistical inference …
a standard normal distribution; it can be used for density estimation and statistical inference …
Numerical methods for mean field games and mean field type control
M Lauriere - Mean field games, 2021 - books.google.com
Mean Field Games (MFG) have been introduced to tackle games with a large number of
competing players. Considering the limit when the number of players is infinite, Nash …
competing players. Considering the limit when the number of players is infinite, Nash …
Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games I: The ergodic case
R Carmona, M Laurière - SIAM Journal on Numerical Analysis, 2021 - SIAM
We propose two algorithms for the solution of the optimal control of ergodic McKean--Vlasov
dynamics. Both algorithms are based on approximations of the theoretical solutions by …
dynamics. Both algorithms are based on approximations of the theoretical solutions by …
An introduction to mean field game theory
These notes are an introduction to Mean Field Game (MFG) theory, which models differential
games involving infinitely many interacting players. We focus here on the Partial Differential …
games involving infinitely many interacting players. We focus here on the Partial Differential …
Alternating the population and control neural networks to solve high-dimensional stochastic mean-field games
We present APAC-Net, an alternating population and agent control neural network for
solving stochastic mean-field games (MFGs). Our algorithm is geared toward high …
solving stochastic mean-field games (MFGs). Our algorithm is geared toward high …
Proximal methods for stationary mean field games with local couplings
We address the numerical approximation of mean field games with local couplings. For
power-like Hamiltonians, we consider a stationary system and also a system involving …
power-like Hamiltonians, we consider a stationary system and also a system involving …
Computational methods for first-order nonlocal mean field games with applications
We introduce a novel framework to model and solve first-order mean field game systems
with nonlocal interactions, extending the results in [L. Nurbekyan and J. Saúde, Port. Math …
with nonlocal interactions, extending the results in [L. Nurbekyan and J. Saúde, Port. Math …
Lagrangian, Eulerian and Kantorovich formulations of multi-agent optimal control problems: equivalence and gamma-convergence
This paper is devoted to the study of multi-agent deterministic optimal control problems. We
initially provide a thorough analysis of the Lagrangian, Eulerian and Kantorovich …
initially provide a thorough analysis of the Lagrangian, Eulerian and Kantorovich …
[HTML][HTML] On monotonicity conditions for mean field games
PJ Graber, AR Mészáros - Journal of Functional Analysis, 2023 - Elsevier
In this paper we propose two new monotonicity conditions that could serve as sufficient
conditions for uniqueness of Nash equilibria in mean field games. In this study we aim for …
conditions for uniqueness of Nash equilibria in mean field games. In this study we aim for …