Policy Space Diversity for Non-Transitive Games

Published: 21 Sept 2023, Last Modified: 02 Nov 2023NeurIPS 2023 posterEveryoneRevisionsBibTeX
Keywords: Policy Diversity, Policy-Space Response Oracles, Nash Equilibrium, Multi-agent Reinforcement Learning
TL;DR: A new and better-justified policy diversity regularization for improving the Nash Equilibrium approximation in Policy-Space Response Oracles.
Abstract: Policy-Space Response Oracles (PSRO) is an influential algorithm framework for approximating a Nash Equilibrium (NE) in multi-agent non-transitive games. Many previous studies have been trying to promote policy diversity in PSRO. A major weakness with existing diversity metrics is that a more diverse (according to their diversity metrics) population does not necessarily mean (as we proved in the paper) a better approximation to a NE. To alleviate this problem, we propose a new diversity metric, the improvement of which guarantees a better approximation to a NE. Meanwhile, we develop a practical and well-justified method to optimize our diversity metric using only state-action samples. By incorporating our diversity regularization into the best response solving of PSRO, we obtain a new PSRO variant, \textit{Policy Space Diversity} PSRO (PSD-PSRO). We present the convergence property of PSD-PSRO. Empirically, extensive experiments on single-state games, Leduc, and Goofspiel demonstrate that PSD-PSRO is more effective in producing significantly less exploitable policies than state-of-the-art PSRO variants.
Submission Number: 9686