A self-learning evolutionary chess program (2004)
| Venue: | Proceedings of the IEEE |
| Citations: | 25 - 0 self |
BibTeX
@INPROCEEDINGS{Fogel04aself-learning,
author = {David B. Fogel and Timothy J. Hays and Sarah L. Hahn and James Quon},
title = {A self-learning evolutionary chess program},
booktitle = {Proceedings of the IEEE},
year = {2004},
pages = {1947--1954}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
A central challenge of artificial intelligence is to create machines that can learn from their own experience and perform at the level of human experts. Using an evolutionary algorithm, a computer program has learned to play chess by playing games against itself. The program learned to evaluate chessboard configurations by using the positions of pieces, material and positional values, and neural networks to assess specific sections of the chessboard. During evolution, the program improved its play by almost 400 rating points. Testing under simulated tournament conditions against Pocket Fritz 2.0 indicated that the evolved program performs above the master level. Keywords—Chess, computational intelligence, evolutionary computation, machine learning, neural networks. I.
Keyphrases
self-learning evolutionary chess program neural network tournament condition specific section rating point pocket fritz central challenge chessboard configuration computational intelligence evolved program performs evolutionary computation keywords chess computer program positional value evolutionary algorithm machine learning master level human expert artificial intelligence
