Observing the Evolution of Neural Networks Learning to Play the Game of Othello
Authors:
- S.Y. ChongSCS.Y. Chong
- M.K. TanMTM.K. Tan
- J.D. WhiteJWJ.D. White
- 6 June 2005
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Evolutionary Computation
- Vol. 9 (3) , 240-251
Abstract
A study was conducted to find out how game-playing strategies for Othello (also known as reversi) can be learned without expert knowledge. The approach used the coevolution of a fixed-architecture neural-network-based evaluation function combined with a standard minimax search algorithm. Comparisons between evolving neural networks and computer players that used deterministic strategies allowed evolution to be observed in real-time. Neural networks evolved to outperform the computer players playing at higher ply-depths, despite being handicapped by playing black and using minimax at ply-depth of two. In addition, the playing ability of the population progressed from novice, to intermediate, and then to master's level. Individual neural networks discovered various game-playing strategies, starting with positional and later mobility. These results show that neural networks can be evolved as evaluation functions, despite the general difficulties associated with this approach. Success in this case was due to a simple spatial preprocessing layer in the neural network that captured spatial information, self-adaptation of every weight and bias of the neural network, and a selection method that allowed a diverse population of neural networks to be carried forward from one generation to the next.Keywords
This publication has 39 references indexed in Scilit:
- Games, computers, and artificial intelligenceArtificial Intelligence, 2002
- Parameter control in evolutionary algorithmsIEEE Transactions on Evolutionary Computation, 1999
- Evolving neural networks to play checkers without relying on expert knowledgeIEEE Transactions on Neural Networks, 1999
- Combining mutation operators in evolutionary programmingIEEE Transactions on Evolutionary Computation, 1998
- A new evolutionary system for evolving artificial neural networksIEEE Transactions on Neural Networks, 1997
- Exploring self-adaptive methods to improve the efficiency of generating approximate solutions to traveling salesman problems using evolutionary programming1997
- Discovering Complex Othello Strategies through Evolutionary Neural NetworksConnection Science, 1995
- An introduction to simulated evolutionary optimizationIEEE Transactions on Neural Networks, 1994
- The development of a world class Othello programArtificial Intelligence, 1990
- A world-championship-level Othello programArtificial Intelligence, 1982