An Empirical Comparison of Non-adaptive, Adaptive and Self-Adaptive Co-evolution for Evolving Artificial Neural Network Game Players

This paper compares the implementation of the non-adaptive, adaptive, and self-adaptive co-evolution for evolving artificial neural networks (ANNs) that act as game players for the game of Tic-Tac-Toe (TTT). The objective of this study is to investigate and empirically compare these three different approaches for tuning strategy parameters´ in co-evolutionary algorithms in evolving the ANN game-playing agents. The results indicate that the non-adaptive and adaptive co-evolution systems performed better than the self-adaptive co-evolution system when suitable strategy parameters were utilized. The adaptive co-evolution system was also found to possess higher evolutionary stability compared to the other systems and was also successful in synthesizing ANNs with high TTT playing strength both as the first as well as second players