Toward Modeling Player-Specific Chess Behaviors

TL;DR

This paper introduces a champion-specific chess modeling approach that uses a novel behavioral metric to better emulate individual players' styles, moving beyond traditional move accuracy assessments.

Contribution

It adapts the Maia-2 model with champion-specific embeddings and a limited MCTS, and proposes a Jensen-Shannon divergence-based metric for evaluating stylistic fidelity.

Findings

MCTS integration reduces move accuracy but enhances stylistic similarity.

The new metric effectively distinguishes individual players based on move distributions.

Results show improved behavioral alignment with historical champions.

Abstract

While artificial intelligence has achieved superhuman performance in chess, developing models that accurately emulate the individualized decision-making styles of human players remains a significant challenge. Existing human-like chess models capture general population behaviors based on skill levels but fail to reproduce the behavioral characteristics of specific historical champions. Furthermore, the standard evaluation metric, move accuracy, inherently penalizes natural human variance and ignores long-term behavioral consistency, leading to an incomplete assessment of stylistic fidelity. To address these limitations, an architecture is proposed that adapts the unified Maia-2 model to champion-specific embeddings, further enhanced by the integration of a limited Monte Carlo Tree Search (MCTS) process to enrich tactical exploration during move selection. To robustly evaluate this approach, a novel behavioral metric based on the Jensen-Shannon divergence is introduced. By compressing high-dimensional board representations into a latent space using an AutoEncoder and Uniform Manifold Approximation and Projection (UMAP), move distributions are discretized on a common grid to compare behavioral similarities. Results across 16 historical world champions indicate that while integrating MCTS decreases standard move accuracy, it improves stylistic alignment according to the proposed metric, substantially reducing the average Jensen-Shannon divergence. Ultimately, the proposed metric successfully discriminates between individual players and provides promising evidence toward more comprehensive evaluations of behavioral alignment between players and AI models.