Title :
A Coevolutionary Model for The Virus Game
Author :
Cowling, P.I. ; Naveed, M.H. ; Hossain, M.A.
Author_Institution :
Dept. of Comput., Bradford Univ.
Abstract :
In this paper, coevolution is used to evolve artificial neural networks (ANN) which evaluate board positions of a two player zero-sum game (the virus game). The coevolved neural networks play at a level that beats a group of strong hand-crafted AI players. We investigate the performance of coevolution starting from random initial weights and starting with weights that are tuned by gradient based adaptive learning methods (backpropagation, RPROP and iRPROP). The results of coevolutionary experiments show that pre training of the population is highly effective in this case
Keywords :
backpropagation; computer games; evolutionary computation; gradient methods; neural nets; artificial neural networks; board position evaluation; coevolutionary model; gradient based adaptive learning; resilient backpropagation; two-player zero-sum game; virus game; Artificial neural networks; Backpropagation; Computer errors; Computer networks; Electronic mail; Evolution (biology); Learning systems; Neural networks; Supervised learning; Unsupervised learning;
Conference_Titel :
Computational Intelligence and Games, 2006 IEEE Symposium on
Conference_Location :
Reno, NV
Print_ISBN :
1-4244-0464-9
DOI :
10.1109/CIG.2006.311680
