Learning in Mean Field Games: the Fictitious Play

Cardaliaguet, Pierre; Hadikhanloo, Saeed

Cardaliaguet, Pierre; Hadikhanloo, Saeed (2015), Learning in Mean Field Games: the Fictitious Play, ESAIM: Control, Optimisation and Calculus of Variations, 23, 2, p. 569-591. 10.1051/cocv/2016004

Type

Article accepté pour publication ou publié

External document link

https://hal.archives-ouvertes.fr/hal-01179503

Date

2015-07

Journal name

ESAIM: Control, Optimisation and Calculus of Variations

Volume

Number

Pages

569-591

Publication identifier

10.1051/cocv/2016004

Metadata

Show full item record

Author(s)

Cardaliaguet, Pierre
CEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
Hadikhanloo, Saeed
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]

Abstract (EN)

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.

Subjects / Keywords

Mean field games; learning