Evolved neural networks learning Othello strategies
Authors:
- 1 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 3, 2222-2229
Abstract
Evolutionary computation was used to train neural networks to learn the play the game of Othello. Each neural network represents a strategy based on board evaluations of the game tree generated by a minimax search algorithm. Networks competed against each other in tournament play and selection used to eliminate those that performed poorly relative to other networks. Self-adaptation was used to mutate the weights and biases of surviving neural networks to generate offspring. By monitoring the evolutionary behavior over 1000 generations through game competitions with computer players playing at higher ply-depths using deterministic evaluations, the networks are shown to coevolve with the style of game play progressing from random to positional and finally to mobility strategy.Keywords
This publication has 10 references indexed in Scilit:
- Using evolutionary programing to create neural networks that are capable of playing tic-tac-toe2002
- Anaconda defeats Hoyle 6-0: a case study competing an evolved checkers program against commercially available software2002
- Improving heuristic mini-max search by supervised learningArtificial Intelligence, 2002
- Evolution, neural networks, games, and intelligenceProceedings of the IEEE, 1999
- Evolving neural networks to play checkers without relying on expert knowledgeIEEE Transactions on Neural Networks, 1999
- Co-Evolution in the Successful Learning of Backgammon StrategyMachine Learning, 1998
- Discovering Complex Othello Strategies through Evolutionary Neural NetworksConnection Science, 1995
- The development of a world class Othello programArtificial Intelligence, 1990
- Strategy Knowledge and Strategy Change in Skilled Performance: A Study of the Game OthelloThe American Journal of Psychology, 1990
- A world-championship-level Othello programArtificial Intelligence, 1982