Scaling up Mean Field Games with Online ...
Type de document :
Pré-publication ou Document de travail
Titre :
Scaling up Mean Field Games with Online Mirror Descent
Auteur(s) :
Perolat, Julien [Auteur]
Perrin, Sarah [Auteur]
Scool [Scool]
Elie, Romuald [Auteur]
Laurière, Mathieu [Auteur]
Piliouras, Georgios [Auteur]
Geist, Matthieu [Auteur]
Tuyls, Karl [Auteur]
Pietquin, Olivier [Auteur]
Perrin, Sarah [Auteur]
Scool [Scool]
Elie, Romuald [Auteur]
Laurière, Mathieu [Auteur]
Piliouras, Georgios [Auteur]
Geist, Matthieu [Auteur]
Tuyls, Karl [Auteur]
Pietquin, Olivier [Auteur]
Discipline(s) HAL :
Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Informatique et théorie des jeux [cs.GT]
Informatique [cs]/Système multi-agents [cs.MA]
Informatique [cs]/Réseau de neurones [cs.NE]
Informatique [cs]/Informatique et théorie des jeux [cs.GT]
Informatique [cs]/Système multi-agents [cs.MA]
Informatique [cs]/Réseau de neurones [cs.NE]
Résumé en anglais : [en]
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 ...
Lire la suite >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.Lire moins >
Lire la suite >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.Lire moins >
Langue :
Anglais
Collections :
Source :
Fichiers
- http://arxiv.org/pdf/2103.00623
- Accès libre
- Accéder au document
- 2103.00623
- Accès libre
- Accéder au document