Scaling up Mean Field Games with Online Mirror Descent - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2021

Scaling up Mean Field Games with Online Mirror Descent

Julien Perolat
  • Fonction : Auteur
Sarah Perrin
  • Fonction : Auteur
Romuald Elie
  • Fonction : Auteur
Mathieu Laurière
  • Fonction : Auteur
Georgios Piliouras
  • Fonction : Auteur
Matthieu Geist
  • Fonction : Auteur
  • PersonId : 790158
  • IdRef : 142341819
Karl Tuyls
  • Fonction : Auteur
Olivier Pietquin
  • Fonction : Auteur

Résumé

We address scaling up equilibrium computation in Mean Field Games (MFGs) using Online Mirror Descent (OMD). We show that continuous-time OMD provably converges to a Nash equilibrium under a natural and well-motivated set of monotonicity assumptions. This theoretical result nicely extends to multi-population games and to settings involving common noise. A thorough experimental investigation on various single and multi-population MFGs shows that OMD outperforms traditional algorithms such as Fictitious Play (FP). We empirically show that OMD scales up and converges significantly faster than FP by solving, for the first time to our knowledge, examples of MFGs with hundreds of billions states. This study establishes the state-of-the-art for learning in large-scale multi-agent and multi-population games.

Dates et versions

hal-03416235 , version 1 (05-11-2021)

Identifiants

Citer

Julien Perolat, Sarah Perrin, Romuald Elie, Mathieu Laurière, Georgios Piliouras, et al.. Scaling up Mean Field Games with Online Mirror Descent. 2021. ⟨hal-03416235⟩
12 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More