Simulating Human Grandmasters: Evolution and Coevolution of Evaluation Functions
This work addresses the challenge of developing high-performance AI for chess by learning directly from human expertise, representing a novel approach rather than an incremental improvement.
The paper tackled the problem of creating a grandmaster-level chess evaluation function by using genetic algorithms with supervised and unsupervised learning from human game databases, resulting in a program that outperforms a two-time World Computer Chess Champion.
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.