Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization

Abstract

We propose the first loss function for approximate Nash equilibria of normal-form games that is amenable to unbiased Monte Carlo estimation. This construction allows us to deploy standard non-convex stochastic optimization techniques for approximating Nash equilibria, resulting in novel algorithms with provable guarantees. We complement our theoretical analysis with experiments demonstrating that stochastic gradient descent can outperform previous state-of-the-art approaches.

Authors

Ian Gemp, Luke Marris, Georgios Piliouras

Venue

ICLR 2024