Publication
Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess
Felix Helfenstein; Jannis Blüml; Johannes Czech; Kristian Kersting
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2401.16852, Pages 1-31, arXiv, 2024.
Abstract
In games like chess, strategy evolves dramatically
across distinct phases — the opening, middlegame, and endgame
each demand different forms of reasoning and decision-making.
Yet, many modern chess engines rely on a single neural network
to play the entire game uniformly, often missing opportunities
to specialize. In this work, we introduce M2CTS, a modular
framework that combines Mixture of Experts with Monte Carlo
Tree Search to adapt strategy dynamically based on game
phase. We explore three different methods for training the
neural networks: Separated Learning, Staged Learning and
Weighted Learning. By routing decisions through specialized
neural networks trained for each phase, M2CTS improves both
computational efficiency and playing strength. In experiments
on chess, M2CTS achieves up to +122 Elo over standard single-
model baselines and shows promising generalization to multi-
agent domains such as Pommerman. These results highlight
how modular, phase-aware systems can better align with the
structured nature of games and move us closer to human-like
behavior in dividing a problem into many smaller units.