Mean Field Games with Ergodic cost for Discrete Time Markov Processes

Abstract

We consider mean field games with ergodic cost in the framework of a general discrete time controlled Markov processes. The state space of the processes is given by a general $\sigma$-compact Polish space. Under certain conditions, we show the existence of a mean field game equilibrium. We also study the $N$-person game where the players interacts with each other via their empirical measure. We show that the $N$-person game has Nash equilibrium and as $N$ tends to infinity the equilibria converge to a mean field game solution.

30 pages. Comments are most welcome

Cited by in corpus (10)

• On Solutions of Mean Field Games with Ergodic Cost
• Actor-Critic Provably Finds Nash Equilibria of Linear-Quadratic Mean-Field Games
• Mean Field Markov Decision Processes
• Geometry of Information Structures, Strategic Measures and associated Control Topologies
• Provable Fictitious Play for General Mean-Field Games
• Learning in Discounted-cost and Average-cost Mean-field Games
• Discrete-time Risk-sensitive Mean-field Games
• Discrete-time average-cost mean-field games on Polish spaces
• Binary Mean Field Stochastic Games: Stationary Equilibria and Comparative Statics
• Value Iteration Algorithm for Mean-field Games