Learning in mean field games: The fictitious play.

Authors

CARDALIAGUET Pierre
HADIKHANLOO Saeed

Publication date

2017

Publication type

Journal Article

Summary 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.

Publisher

EDP Sciences

See the publication

Topics of the publication

Mean field games
Learning

Themes detected by scanR from retrieved publications. For more information, see https://scanr.enseignementsup-recherche.gouv.fr