Back to Search Start Over

Scalable Deep Reinforcement Learning Algorithms for Mean Field Games

Authors :
Laurière, Mathieu
Perrin, Sarah
Girgin, Sertan
Muller, Paul
Jain, Ayush
Cabannes, Theophile
Piliouras, Georgios
Pérolat, Julien
Élie, Romuald
Pietquin, Olivier
Geist, Matthieu
Laurière, Mathieu
Perrin, Sarah
Girgin, Sertan
Muller, Paul
Jain, Ayush
Cabannes, Theophile
Piliouras, Georgios
Pérolat, Julien
Élie, Romuald
Pietquin, Olivier
Geist, Matthieu
Publication Year :
2022

Abstract

Mean Field Games (MFGs) have been introduced to efficiently approximate games with very large populations of strategic agents. Recently, the question of learning equilibria in MFGs has gained momentum, particularly using model-free reinforcement learning (RL) methods. One limiting factor to further scale up using RL is that existing algorithms to solve MFGs require the mixing of approximated quantities such as strategies or $q$-values. This is far from being trivial in the case of non-linear function approximation that enjoy good generalization properties, e.g. neural networks. We propose two methods to address this shortcoming. The first one learns a mixed strategy from distillation of historical data into a neural network and is applied to the Fictitious Play algorithm. The second one is an online mixing method based on regularization that does not require memorizing historical data or previous estimates. It is used to extend Online Mirror Descent. We demonstrate numerically that these methods efficiently enable the use of Deep RL algorithms to solve various MFGs. In addition, we show that these methods outperform SotA baselines from the literature.

Details

Database :
OAIster
Publication Type :
Electronic Resource
Accession number :
edsoai.on1333758577
Document Type :
Electronic Resource