Playing Tic-Tac-Toe Using Genetic Neural Network with Double Transfer Functions

Sai Ho Ling, Hak Keung Lam

.

DOI: 10.4236/jilsa.2011.31005                

Abstract

Computational intelligence is a powerful tool for game development. In this paper, an algorithm of playing the game Tic-Tac-Toe with computational intelligence is developed. This algorithm is learned by a Neural Network with Double Transfer functions (NNDTF), which is trained by genetic algorithm (GA). In the NNDTF, the neuron has two transfer functions and exhibits a node-to-node relationship in the hidden layer that enhances the learning ability of the net-work. A Tic-Tac-Toe game is used to show that the NNDTF provide a better performance than the traditional neural network does.

Keywords

Game, Genetic Algorithm, Neural Network

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	H. J. V. D. Herik, J. W. H. M. Uiterwijk and J. V. Rijswijck, “Games Solved: Now and in the Future,” Artificial Intelligence, Vol. 134, No. 1-2, 2002, pp. 277-311. doi:10. 1016/S0004-3702(01)00152-7
[2]	H. J. V. D. Herik and I. S. Herschberg, “The Construction of an Omniscient Endgame Data Base,” ICCA Journal, Vol. 8, No. 2, 1985, pp. 66-87.
[3]	L. V. Allis, M. V. D. Meulen and. V. D. Herik, “Proof- Number Search,” Artificial Intelligence, Vol. 66, No.1, 1994, pp. 91-124. doi:10.1016/0004-3702(94)90004-3
[4]	D. B. Fogel and K. Chellapilla, “Verifying Anaconda’s Expert Rating by Competing against Chinook: Experiments in Co-Evolving a Neural Checkers Player,” Neurcomputing, Vol. 42, No. 1-4, 2002, pp. 69-86. doi:10.10 16/S0925-2312(01)00594-X
[5]	K. Chellapilla and D. B. Fogel, “Evolving Neural Networks to Play Checkers without Relying on Expert Knowledge,” IEEE Transactions on Neural Networks, Vol. 10, No. 6, 1999, pp. 1382-1391. doi:10.1109/72.80 9083
[6]	K. Chellapilla and D. B. Fogel, “Evolving an Expert Checkers Playing Program without Using Human Expertise,” IEEE Transactions on Evolutionary Com-putation, Vol. 5, No. 4, 2001, pp. 422-428. doi:10.1109/4235.94 2536
[7]	K. Chellapilla and D. B. Fogel, “Autonomous Evolution of Topographic Regularities in Artificial Neural Net-works,” Neural Computation, Vol. 22, No. 7, 2010, pp. 1860-1898. doi:10.1162/neco.2010.06-09-1042
[8]	G. Tesauro, “Programming Backgammon Using Self- Teaching Neural Nets,” Artificial Intelligence, Vol. 134, No. 1-2, 2002, pp. 181-199. doi:10.1016/S0004-3702(01) 00110-2
[9]	S. Y. Chong, M. K. Tan and J. D. White, “Observing the Evolution of Neural Networks Learning to Play the Game of Othello,” IEEE Transactions on Evolutionary Computation, Vol. 9, No. 3, 2005, pp. 422-428. doi:10.1109/TE- VC.2005.843750
[10]	D. E. Beal and M. C. Smith, “Random Evolutions in Chess,” ICCA Journal, Vol. 17, No. 1, 1994, pp. 3-9.
[11]	F. H. F. Leung, H. K. Lam, S. H. Ling and P. K. S. Tam, “Tuning of the Structure and Parameters of Neural Network Using an Improved Genetic Algorithm,” IEEE Transactions on Neural Networks, Vol.14, No. 1, 2003, pp. 79- 88. doi:10.1109/TNN.2002.804317
[12]	M. Brown and C. Harris, “Neuralfuzzy Adaptive Modeling and Control,” Prentice Hall, Upper Saddle River, 1994.
[13]	S. H. Ling, F. H. F. Leung, H. K. Lam, Y. S. Lee and P. K. S. Tam, “A Novel GA-Based Neural Network for Short-Term Load Forecasting,” IEEE Transactions on Industrial Electronics, Vol. 50, No. 4, 2003, pp. 793-799. doi:10.1109/TIE.2003.814869
[14]	J. H. Holland, “Adaptation in Natural and Artificial Systems,” University of Michigan Press, Ann Arbor, 1975.
[15]	D. T. Pham and D. Karaboga, “Intelligent Optimization Techniques, Genetic Algo-rithms, Tabu Search, Simulated Annealing and Neural Net-works,” Springer-Verlag, New York, 2000.
[16]	Z. Michale-wicz, “Genetic Algorithm + Data Structures = Evolution Pro-grams,” 2nd Edition, Springer-Verlag, New York, 1994.
[17]	S. Haykin, “Neural networks: A Comprehensive Foundation,” 2nd Edition, Prentice Hall, Upper Saddle River, 1999.