Anahtarcı, BerkayKarıksız, Can DehaSaldı, N.2024-02-202024-02-2020231532-4435http://hdl.handle.net/10679/9177We consider learning approximate Nash equilibria for discrete-time mean-field games with stochastic nonlinear state dynamics subject to both average and discounted costs. To this end, we introduce a mean-field equilibrium (MFE) operator, whose fixed point is a mean-field equilibrium, i.e., equilibrium in the infinite population limit. We first prove that this operator is a contraction, and propose a learning algorithm to compute an approximate mean-field equilibrium by approximating the MFE operator with a random one. Moreover, using the contraction property of the MFE operator, we establish the error analysis of the proposed learning algorithm. We then show that the learned mean-field equilibrium constitutes an approximate Nash equilibrium for finite-agent games.engopenAccessAttribution 4.0 Internationalhttps://creativecommons.org/licenses/by/4.0/article24001111696000001Mean-field gamesApproximate Nash equilibriumFitted Q-iteration algo-rithmDiscounted-costAverage-cost