Pattern Acquisition and Comparative Analysis in the Game of Go

Angel Alberto Sesma Gonzalez et al. /December 19, 2025

Abstract
The game of Go represents a major challenge for artificial as well as human intelligences due to its profound complexity.

Although computer programs capable of playing Go have existed for decades, the period from 2015 to 2025 has marked a turning point, with these systems achieving—and even exceeding—professional human performance. A notable shift in gameplay strategy emerged around 2016, driven by the adoption of unconventional yet effective moves demonstrated by AI programs, challenging previous conventions of preferred moves.

Nowadays, the process of learning Go has evolved from traditional knowledge transfer, based on centuries of established conventions regarding strategy, positional judgement and move value to modern trends developed by AI playing style, lacking the explanatory heuristics inherent in both human style of playing and oral tradition.

Facing this new challenge, we rely on our curiosity to understand our opponents’ moves beyond technological and language barriers as we continue to explore the mysterious depths of this timeless game.

Keywords: Statistical analysis, Pattern recognition, AI interpretability,
Modern theory, Style evolution, Professional Games, Computational Go.