Multi-Agent Training beyond Zero-Sum with Correlated Equilibrium Meta-Solvers
This addresses the challenge of multi-agent training beyond zero-sum games for AI and game theory researchers, representing a novel extension rather than an incremental improvement.
The paper tackles the problem of training agents in n-player, general-sum extensive form games, proposing the JPSRO algorithm that provably converges to an equilibrium and introducing MGCE as a computationally efficient solution for correlated equilibrium selection, with experiments demonstrating convergence.
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.