Generalized conditional gradient and learning in potential mean field games

MaRDI QIDQ6377492zbMATH OpenFDO

Authors J. Frédéric Bonnans, Pierre Lavigne, Laurent Pfeiffer

Publication date 13 September 2021

Abstract: We apply the generalized conditional gradient algorithm to potential mean field games and we show its well-posedeness. It turns out that this method can be interpreted as a learning method called fictitious play. More precisely, each step of the generalized conditional gradient method amounts to compute the best-response of the representative agent, for a predicted value of the coupling terms of the game. We show that for the learning sequence $delt{a}_k=2/(k+2)$, the potential cost converges in $O(1/k)$, the exploitability and the variables of the problem (distribution, congestion, price, value function and control terms) converge in $O(1/sqrtk)$, for specific norms.

This page was built for publication: Generalized conditional gradient and learning in potential mean field games

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6377492)