Share Email Print
cover

Proceedings Paper

New results on evolving strategies in chess
Author(s): David B. Fogel; Tim Hays
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Evolutionary algorithms have been used for learning strategies in diverse games, including Othello, backgammon, checkers, and chess. The paper provides a brief background on efforts in evolutionary learning in chess, and presents recent results on using coevolution to learn strategies by improving existing nominal strategies. Over 10 independent trials, each executed for 50 generations, a simple evolutionary algorithm was able to improve a nominal strategy that was based on material value and positional value adjustments associated with individual pieces. The improvement was estimated at over 284 rating points, taking a Class A player and evolving it into an expert.

Paper Details

Date Published: 30 December 2003
PDF: 8 pages
Proc. SPIE 5200, Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation VI, (30 December 2003); doi: 10.1117/12.512624
Show Author Affiliations
David B. Fogel, Natural Selection, Inc. (United States)
Tim Hays, Natural Selection, Inc. (United States)


Published in SPIE Proceedings Vol. 5200:
Applications and Science of Neural Networks, Fuzzy Systems, and Evolutionary Computation VI
Bruno Bosacchi; David B. Fogel; James C. Bezdek, Editor(s)

© SPIE. Terms of Use
Back to Top