# Mean-Field Games Under Model Uncertainty

arXiv: https://arxiv.org/abs/2601.12226 · HTML: https://mlsanity.com/paper/2601.12226/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jan 2026.

## Built on by (most cited first, 3 of 3)

- [Robust Q-learning for mean-field control under Wasserstein uncertainty in common noise](https://mlsanity.com/paper/2606.20356/) (2026)
- [Stationary Robust Mean-Field Games under Model Mismatches](https://mlsanity.com/paper/2606.22579/) (2026)
- [Beyond Nominal Equilibria: Risk-Averse Multi-Population Mean-Field Games](https://mlsanity.com/paper/2610.09244/) (2026)

## Abstract (arXiv)

We study discrete-time, finite-state mean-field games (MFGs) under model uncertainty, where agents face ambiguity about the state transition probabilities. Each agent maximizes its expected payoff against the worst-case transitions within an uncertainty set. Unlike in classical MFGs, model uncertainty renders the population distribution flow stochastic. This leads us to consider strategies that depend on both individual states and the realized distribution of the population. Our main results establish the asymptotic relationship between N-agent games and MFGs: every MFG equilibrium constitutes an varepsilon-Nash equilibrium for sufficiently large populations, and conversely, limits of N-agent equilibria are MFG equilibria. We also prove the existence of equilibria for finite-agent games and construct a solvable mean-field example with closed-form solutions.