Learning in Mean Field Games: the Fictitious Play

Pierre Cardaliaguet (1) , Saeed Hadikhanloo (2)

1 CEREMADE - CEntre de REcherches en MAthématiques de la DEcision
2 LAMSADE - Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision

Mean Field Game systems describe equilibrium configurations in differential games with infinitely many infinitesimal interacting agents. We introduce a learning procedure (similar to the Fictitious Play) for these games and show its convergence when the Mean Field Game is potential.

Domaines: Optimisation et contrôle [math.OC]

Pierre Cardaliaguet, Saeed Hadikhanloo. Learning in Mean Field Games: the Fictitious Play. 2015. ⟨hal-01179503v1⟩