Blondie25
Blondie25,
an evolutionary chess program by David B. Fogel and Timothy J. Hays, supported by James Quon and Sarah L. Hahn. Blondie25 improved its play by almost 400 rating points during evolution [1].
New Results in Evolving Chess
Quote from the Press Release, May 22, 2006 [2]
Blondie25 is the result of over 8000 generations of variation and selection, simulated on a computer, in which a computer chess-playing program plays games against variations of itself to learn how to improve its play. Blondie25 includes mechanisms for learning the values of the pieces, their locations on the chessboard, and also uses neural networks to assess the formation of pieces in different areas of the board.
See also
Publications
- David B. Fogel, Timothy J. Hays (2003). New Results on Evolving Strategies in Chess. Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation VI
- David B. Fogel, Timothy J. Hays, Sarah L. Hahn, James Quon (2004). A Self-Learning Evolutionary Chess Program. Proceedings of the IEEE, Vol. 92, No. 12, CiteSeerX
- David B. Fogel, Timothy J. Hays, Sarah L. Hahn, James Quon (2005). Further Evolution of a Self-Learning Chess Program. IEEE Symposium on Computational Intelligence & Games, CiteSeerX
- David B. Fogel, Timothy J. Hays, Sarah L. Hahn, James Quon (2006). The Blondie25 Chess Program Competes Against Fritz 8.0 and a Human Chess Master. IEEE Symposium on Computational Intelligence & Games » Fritz
External Links
References
- ↑ David B. Fogel, Timothy J. Hays, Sarah L. Hahn, James Quon (2004). A Self-Learning Evolutionary Chess Program. Proceedings of the IEEE, Vol. 92 No. 12, CiteSeerX
- ↑ Natural Selection, Inc. Presents New Results in Evolving Chess Programs: Two Milestones in Self-Learning Chess Achieved | Natural Selection, Inc (as of October 24, 2018 no longer avalable)
