AN INVESTIGATION OF AN INTEGRATION OF INDIVIDUAL AND SOCIAL LEARNING IN AN EVOLUTIONARY APPROACH TO THE GAME OF TIC-TAC-TOE

Abstract

In this paper, we investigate an integration of individual and social learning, utilising evolutionary neural networks. Individual learning takes place by playing against the nearly perfect player. Social learning allows poor performing players to learn from those players, which are playing at a higher level. There are two types of experiments in this work, i.e. the experiment with social learning and the experiment without the social learning. The feed forward neural networks are evolved via evolutionary strategies and no knowledge incorporate in this work. Our experiments show that learning the experiment with social learning statistically significant giving better result than the experiment without social learning.