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.
Cite
Text
Gemp et al. "Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization." International Conference on Learning Representations, 2024.Markdown
[Gemp et al. "Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization." International Conference on Learning Representations, 2024.](https://mlanthology.org/iclr/2024/gemp2024iclr-approximating/)BibTeX
@inproceedings{gemp2024iclr-approximating,
title = {{Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization}},
author = {Gemp, Ian and Marris, Luke and Piliouras, Georgios},
booktitle = {International Conference on Learning Representations},
year = {2024},
url = {https://mlanthology.org/iclr/2024/gemp2024iclr-approximating/}
}