NfgTransformer: Equivariant Representation Learning for Normal-form Games
Siqi Liu, Luke Marris, Georgios Piliouras, Ian Gemp, Nicolas Heess
Abstract
Normal-form games (NFGs) are the fundamental model of *strategic interaction*. We study their representation using neural networks. We describe the inherent equivariance of NFGs --- any permutation of strategies describes an equivalent game --- as well as the challenges this poses for representation learning. We then propose the NfgTransformer architecture that leverages this equivariance, leading to state-of-the-art performance in a range of game-theoretic tasks including equilibrium-solving, deviation gain estimation and ranking, with a common approach to NFG representation. We show that the resulting model is interpretable and versatile, paving the way towards deep learning systems capable of game-theoretic reasoning when interacting with humans and with each other.
BibTeX
@inproceedings{
liu2024nfgtransformer,
title={NfgTransformer: Equivariant Representation Learning for Normal-form Games},
author={Siqi Liu and Luke Marris and Georgios Piliouras and Ian Gemp and Nicolas Heess},
booktitle={The Twelfth International Conference on Learning Representations},
year={2024},
url={https://openreview.net/forum?id=4YESQqIys7}
}