TY  - GEN
N1  - © 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/).
EP  - 7491
AV  - public
SP  - 7480
Y1  - 2021///
TI  - Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers
A1  - Marris, Luke
A1  - Muller, Paul
A1  - Lanctot, Marc
A1  - Tuyls, Karl
A1  - Graepel, Thore
UR  - https://proceedings.mlr.press/v139/marris21a.html
PB  - Proceedings of Machine Learning Research
ID  - discovery10187244
N2  - 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.
ER  -