Statistical Feature Combination for the Evaluation of Game Positions

TL;DR

This paper applies statistical methods like logistic regression, Fisher's linear discriminant, and quadratic discriminant to evaluate Othello positions, demonstrating that logistic regression improves game-playing performance.

Contribution

It introduces the use of logistic regression for game position evaluation, showing its superiority over traditional methods in Othello.

Findings

Logistic regression outperforms other statistical methods in evaluation accuracy.

Tournament results favor the logistic regression-based program.

Statistical feature combination enhances game position assessment.

Abstract

This article describes an application of three well-known statistical methods in the field of game-tree search: using a large number of classified Othello positions, feature weights for evaluation functions with a game-phase-independent meaning are estimated by means of logistic regression, Fisher's linear discriminant, and the quadratic discriminant function for normally distributed features. Thereafter, the playing strengths are compared by means of tournaments between the resulting versions of a world-class Othello program. In this application, logistic regression - which is used here for the first time in the context of game playing - leads to better results than the other approaches.