Issue |
ESAIM: COCV
Volume 23, Number 2, April-June 2017
|
|
---|---|---|
Page(s) | 569 - 591 | |
DOI | https://doi.org/10.1051/cocv/2016004 | |
Published online | 18 January 2017 |
Learning in mean field games: The fictitious play
1 Université Paris-Dauphine, PSL Research University, Ceremade, Place du Maréchal de Lattre de Tassigny 75775 Paris cedex 16, France.
cardaliaguet@ceremade.dauphine.fr
2 Université Paris-Dauphine, PSL Research University, Lamsade, Place du Maréchal de Lattre de Tassigny 75775 Paris cedex 16, France.
Received: 7 July 2015
Revised: 27 November 2015
Accepted: 7 January 2016
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.
Mathematics Subject Classification: 35Q91 / 35F21 / 49L25
Key words: Mean field games / learning
© EDP Sciences, SMAI 2017
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.