Authors: Belal Al-Khateeb
Addresses: Department of Computer Science, College of Computer, University of Anbar, Ramadi, Al-Anbar, Iraq
Abstract: In this paper, artificial neural networks are used as function evaluators in order to evolve game playing strategies for the game of tic-tac-toe. The best evolved player is tested against an online perfect tic-tac-toe player, and also against a nearly perfect player which allows 10% random moves and finally against five selected human players. Those players are with different playing abilities. The results are promising, suggesting many other research directions.
Keywords: artificial neural networks; ANNs; tic-tac-toe; evolutionary algorithms; function evaluators.
International Journal of Reasoning-based Intelligent Systems, 2012 Vol.4 No.4, pp.182 - 185
Received: 08 May 2021
Accepted: 12 May 2021
Published online: 27 Jan 2013 *