Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers
Luke Marris, Paul Muller, Marc Lanctot, Karl Tuyls, Thore Graepel
Abstract
Two-player, constant-sum games are well studied in the literature, but there has been limited progress outside of this setting. We propose Joint Policy-Space Response Oracles (JPSRO), an algorithm for training agents in n-player, general-sum extensive form games, which provably converges to an equilibrium. We further suggest correlated equilibria (CE) as promising meta-solvers, and propose a novel solution concept Maximum Gini Correlated Equilibrium (MGCE), a principled and computationally efficient family of solutions for solving the correlated equilibrium selection problem. We conduct several experiments using CE meta-solvers for JPSRO and demonstrate convergence on n-player, general-sum games.
BibTeX
@InProceedings{pmlr-v139-marris21a,
title = {Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers},
author = {Marris, Luke and Muller, Paul and Lanctot, Marc and Tuyls, Karl and Graepel, Thore},
booktitle = {Proceedings of the 38th International Conference on Machine Learning},
pages = {7480--7491},
year = {2021},
editor = {Meila, Marina and Zhang, Tong},
volume = {139},
series = {Proceedings of Machine Learning Research},
month = {18--24 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v139/marris21a/marris21a.pdf},
url = {https://proceedings.mlr.press/v139/marris21a.html},
abstract = {Two-player, constant-sum games are well studied in the literature, but there has been limited progress outside of this setting. We propose Joint Policy-Space Response Oracles (JPSRO), an algorithm for training agents in n-player, general-sum extensive form games, which provably converges to an equilibrium. We further suggest correlated equilibria (CE) as promising meta-solvers, and propose a novel solution concept Maximum Gini Correlated Equilibrium (MGCE), a principled and computationally efficient family of solutions for solving the correlated equilibrium selection problem. We conduct several experiments using CE meta-solvers for JPSRO and demonstrate convergence on n-player, general-sum games.}
}