Tree Search for Simultaneous Move Games via Equilibrium Approximation

TL;DR

This paper introduces a tree search method that approximates equilibrium strategies for simultaneous move games, improving performance on benchmarks like Google Research Football and Starcraft.

Contribution

It adapts perfect information game tree search algorithms to simultaneous move games using equilibrium approximation, achieving superior results.

Findings

Outperforms current MARL algorithms on multiple benchmarks

Effective in cooperative, competitive, and mixed environments

Provides a practical equilibrium approximation method for tree search

Abstract

Neural network supported tree-search has shown strong results in a variety of perfect information multi-agent tasks. However, the performance of these methods on partial information games has generally been below competing approaches. Here we study the class of simultaneous-move games, which are a subclass of partial information games which are most similar to perfect information games: both agents know the game state with the exception of the opponent's move, which is revealed only after each agent makes its own move. Simultaneous move games include popular benchmarks such as Google Research Football and Starcraft. In this study we answer the question: can we take tree search algorithms trained through self-play from perfect information settings and adapt them to simultaneous move games without significant loss of performance? We answer this question by deriving a practical method that attempts to approximate a coarse correlated equilibrium as a subroutine within a tree search. Our algorithm works on cooperative, competitive, and mixed tasks. Our results are better than the current best MARL algorithms on a wide range of accepted baseline environments.