@inproceedings{discovery10187244, year = {2021}, title = {Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers}, publisher = {Proceedings of Machine Learning Research}, journal = {Proceedings of the 38th International Conference on Machine Learning}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {7480--7491}, editor = {M Meila and T Zhang}, volume = {139}, note = {{\copyright} The Authors 2023. Original content in this paper is licensed under the terms of the Creative Commons Attribution 4.0 International (CC BY 4.0) Licence (https://creativecommons.org/licenses/by/4.0/).}, author = {Marris, Luke and Muller, Paul and Lanctot, Marc and Tuyls, Karl and Graepel, Thore}, 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.}, url = {https://proceedings.mlr.press/v139/marris21a.html} }