Mean field regret in discrete time games

Abstract

In this paper, we use mean field games (MFGs) to investigate approximations of N -player games with uniformly symmetrically continuous heterogeneous closed-loop actions. To incorporate agents' risk aversion (beyond the classical expected total costs), we use an abstract evaluation functional for their performance criteria. Centered around the notion of regret, we conduct non-asymptotic analysis on the approximation capability of MFGs from the perspective of state-action distribution without requiring the uniqueness of equilibria. Under suitable assumptions, we first show that scenarios in the N -player games with large N and small average regrets can be well approximated by approximate solutions of MFGs with relatively small regrets. We then show that δ-mean field equilibria can be used to construct ε-equilibria in N -player games. Furthermore, in this general setting, we prove the existence of mean field equilibria.