Discrete-Time Mean Field Type Games: Probabilistic Setup

TL;DR

This paper develops a probabilistic framework for discrete-time, infinite-horizon mean field games with common noises, establishing existence of optimal policies and Nash equilibria under broad conditions.

Contribution

It introduces a general probabilistic setup for mean field games with common noises and randomized actions, connecting MFTGs and MFMGs, and proves existence of equilibria.

Findings

Existence of optimal closed-loop policies in countable state spaces.

Connection between MFTGs and MFMGs via randomization layers.

Example demonstrating the theory with strongly randomized dynamics.

Abstract

We introduce a general probabilistic framework for discrete-time, infinite-horizon discounted Mean Field Type Games (MFTGs) with both global common noise and team-specific common noises. In our model, agents are allowed to use randomized actions, both at the individual level and at the team level. We formalize the concept of Mean Field Markov Games (MFMGs) and establish a connection between closed-loop policies in MFTGs and Markov policies in MFMGs through different layers of randomization. By leveraging recent results on infinite-horizon discounted games with infinite compact state-action spaces, we prove the existence of an optimal closed-loop policy for the original MFTG when the state spaces are at most countable and the action spaces are general Polish spaces. We also present an example satisfying our assumptions, called Mean Field Drift of Intentions, where the dynamics are strongly randomized, and we establish the existence of a Nash equilibrium using our theoretical results.