ICLR 2024oral9 citations
Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization
Ian Gemp, Luke Marris, Georgios Piliouras
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.
game theorystochastic optimizationnash equilbriumnormal-form gamex-armed bandits
BibTeX
@inproceedings{
gemp2024approximating,
title={Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization},
author={Ian Gemp and Luke Marris and Georgios Piliouras},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=cc8h3I3V4E}
}