AI RESEARCH
Reproducing AlphaZero on Tablut: Self-Play RL for an Asymmetric Board Game
arXiv CS.LG
•
ArXi:2604.05476v1 Announce Type: new This work investigates the adaptation of the AlphaZero reinforcement learning algorithm to Tablut, an asymmetric historical board game featuring unequal piece counts and distinct player objectives (king capture versus king escape). While the original AlphaZero architecture successfully leverages a single policy and value head for symmetric games, applying it to asymmetric environments forces the network to learn two conflicting evaluation functions, which can hinder learning efficiency and performance.