Mastering Terra Mystica: Applying Self-Play to Multi-agent Cooperative Board Games
This work addresses the challenge of multi-agent cooperative board game AI for game developers and AI researchers, but it appears incremental as it directly applies existing methods to a new game.
The paper tackled the problem of creating an AI for the complex strategy board game Terra Mystica by applying AlphaZero with a novel state representation, resulting in an AI called AlphaTM that was compared against baselines and human scores.
In this paper, we explore and compare multiple algorithms for solving the complex strategy game of Terra Mystica, hereafter abbreviated as TM. Previous work in the area of super-human game-play using AI has proven effective, with recent break-through for generic algorithms in games such as Go, Chess, and Shogi \cite{AlphaZero}. We directly apply these breakthroughs to a novel state-representation of TM with the goal of creating an AI that will rival human players. Specifically, we present the initial results of applying AlphaZero to this state-representation and analyze the strategies developed. A brief analysis is presented. We call this modified algorithm with our novel state-representation AlphaTM. In the end, we discuss the success and shortcomings of this method by comparing against multiple baselines and typical human scores. All code used for this paper is available at on \href{https://github.com/kandluis/terrazero}{GitHub}.