Markov-Nash equilibria in mean-field games under model uncertainty

TL;DR

This paper develops a framework for mean-field Markov games considering model uncertainty, establishing the existence of equilibria where agents optimize worst-case rewards and demonstrating approximate equilibrium properties in large populations.

Contribution

It introduces a novel mean-field game model under model uncertainty and proves the existence of equilibrium solutions and their approximate Nash properties in large-agent settings.

Findings

Existence of mean-field equilibrium under model uncertainty.

Optimal policies form approximate Nash equilibria in large populations.

Framework accounts for worst-case transition kernels in decision-making.

Abstract

We propose and analyze a framework for mean-field Markov games under model uncertainty. In this framework, a state-measure flow describing the collective behavior of a population affects the given reward function as well as the unknown transition kernel of the representative agent. The agent's objective is to choose an optimal Markov policy in order to maximize her worst-case expected reward, where worst-case refers to the most adverse scenario among all transition kernels considered to be feasible to describe the unknown true law of the environment. We prove the existence of a mean-field equilibrium under model uncertainty, where the agent chooses the optimal policy that maximizes the worst-case expected reward, and the state-measure flow aligns with the agent's state distribution under the optimal policy and the worst-case transition kernel. Moreover, we prove that for suitable multi-agent Markov games under model uncertainty the optimal policy from the mean-field equilibrium forms an approximate Markov-Nash equilibrium whenever the number of agents is large enough.