Toward Modeling Player-Specific Chess Behaviors

2026-05-12

AI Summary

This work addresses the challenge that existing AI models struggle to replicate the idiosyncratic decision-making styles of individual human chess players and lack effective metrics for quantifying behavioral consistency. To model player-specific behavior, the authors extend the Maia-2 architecture with player-specific embeddings and integrate limited Monte Carlo tree search to enhance tactical exploration. They propose a novel behavioral consistency metric based on Jensen–Shannon divergence and employ an autoencoder combined with UMAP to construct a unified behavioral representation space capable of distinguishing stylistic differences across players. Experiments on games from 16 historical world champions demonstrate that, despite a slight reduction in move prediction accuracy, the model achieves significantly improved style alignment, and the proposed metric reliably captures individual behavioral distinctions.

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.

Problem

• player-specific behavior
• chess AI
• behavioral modeling
• stylistic fidelity
• evaluation metric

Innovation

• champion-specific modeling
• Monte Carlo Tree Search
• behavioral alignment
• Jensen-Shannon divergence
• latent space representation