Simulating Human Grandmasters: Evolution and Coevolution of Evaluation Functions

TL;DR

This paper presents a novel approach to developing a chess evaluation function by using genetic algorithms to learn from human grandmaster games, resulting in a program that surpasses top computer chess champions.

Contribution

It introduces the first successful evolution of a grandmaster-level evaluation function solely from human game databases, combining supervised and unsupervised learning.

Findings

Evolved program outperforms two-time World Computer Chess Champion.

First to learn evaluation functions exclusively from human game data.

Demonstrates effectiveness of coevolution in refining chess evaluation.

Abstract

This paper demonstrates the use of genetic algorithms for evolving a grandmaster-level evaluation function for a chess program. This is achieved by combining supervised and unsupervised learning. In the supervised learning phase the organisms are evolved to mimic the behavior of human grandmasters, and in the unsupervised learning phase these evolved organisms are further improved upon by means of coevolution. While past attempts succeeded in creating a grandmaster-level program by mimicking the behavior of existing computer chess programs, this paper presents the first successful attempt at evolving a state-of-the-art evaluation function by learning only from databases of games played by humans. Our results demonstrate that the evolved program outperforms a two-time World Computer Chess Champion.