Injecting Combinatorial Optimization into MCTS: Application to the Board Game boop

TL;DR

This paper introduces a novel approach that integrates Combinatorial Optimization into Monte Carlo Tree Search to enhance game-playing AI, demonstrating significant improvements in performance on the board game boop.

Contribution

The paper presents a new method combining Combinatorial Optimization with MCTS, showing its effectiveness in a new game domain and outperforming standard MCTS baselines.

Findings

Our method beats 96% of the baseline MCTS in boop.

Achieved a 69% win rate against human players.

Ranked 56th worldwide on Board Game Arena.

Abstract

Games, including abstract board games, constitute a convenient ground to create, design, and improve new AI methods. In this field, Monte Carlo Tree Search is a popular algorithm family, aiming to build game trees and explore them efficiently. Combinatorial Optimization, on the other hand, aims to model and solve problems with an objective to optimize and constraints to satisfy, and is less common in Game AI. We believe however that both methods can be combined efficiently, by injecting Combinatorial Optimization into Monte Carlo Tree Search to help the tree search, leading to a novel combination of these two techniques. Tested on the board game boop., our method beats 96% of the time the Monte Carlo Tree Search algorithm baseline. We conducted an ablation study to isolate and analyze which injections and combinations of injections lead to such performances. Finally, we opposed our AI method against human players on the Board Game Arena platform, and reached a 373 ELO rating after 51 boop. games, with a 69% win rate and finishing ranked 56th worldwide on the platform over 5,316 boop. players.