In-Person Poster presentation / poster accept
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games
Samuel Sokota · Ryan D'Orazio · Zico Kolter · Nicolas Loizou · Marc Lanctot · Ioannis Mitliagkas · Noam Brown · Christian Kroer
MH1-2-3-4 #149
Keywords: [ quantal response equilibria ] [ proximal gradient ] [ algorithmic game theory ] [ two-player zero-sum games ] [ mirror descent ] [ Nash equilibria ] [ Variational inequalities ] [ reinforcement learning ] [ Theory ]
This work studies an algorithm, which we call magnetic mirror descent, that is inspired by mirror descent and the non-Euclidean proximal gradient algorithm. Our contribution is demonstrating the virtues of magnetic mirror descent as both an equilibrium solver and as an approach to reinforcement learning in two-player zero-sum games. These virtues include: 1) Being the first quantal response equilibria solver to achieve linear convergence for extensive-form games with first order feedback; 2) Being the first standard reinforcement learning algorithm to achieve empirically competitive results with CFR in tabular settings; 3) Achieving favorable performance in 3x3 Dark Hex and Phantom Tic-Tac-Toe as a self-play deep reinforcement learning algorithm.