🤖 AI Summary
This work addresses the challenge of mastering WallGo—a strategic board game characterized by an exceptionally high game-tree complexity and intricate strategic interactions—by introducing WallZero, the first WallGo agent built upon the AlphaZero framework. WallZero incorporates a customized action encoding scheme and state feature representation, integrated with Monte Carlo tree search, to substantially enhance decision-making efficiency and playing strength. Experimental results demonstrate that WallZero secures, on average, 1.98 times more territory than its opponents and successfully defeats two professional Go players. Furthermore, strategic analysis reveals that opening strategies featured in a Netflix series exhibit greater balance, offering a novel approach to evaluating game fairness and distilling effective strategies.
📝 Abstract
WallGo is a recently introduced strategic board game popularized by the 2025 Netflix series The Devil's Plan. Although played on a small 7 x 7 board, its combination of stone movement and wall placement yields high game-tree complexity and intricate strategic interactions. Despite its growing popularity, WallGo remains underexplored. This paper presents WallZero, an AlphaZero-based agent for the two-player WallGo setting. We introduce tailored action and feature designs to improve playing performance significantly. In the evaluation, WallZero defeats two professional Go players who participated in this study, securing on average 1.98x more territory per game. Beyond its strength, we use WallZero to assess game fairness and identify key strategies for mastering WallGo. Interestingly, our results show that the opening used in the Netflix series yields a more balanced game. Our code is available at https://rlg.iis.sinica.edu.tw/papers/wallzero.