Neuro-Evolution Through Augmenting Topologies Applied To Evolving Neural Networks To Play Othello

Many different approaches to game playing have been suggested including alpha-beta search, temporal difference learning, genetic algorithms, and coevolution. Here, a powerful new algorithm for neuroevolution, Neuro-Evolution for Augmenting Topologies (NEAT), is adapted to the game playing domain. Evolution and coevolution were used to try and develop neural networks capable of defeating an alpha-beta search Othello player. While standard evolution outperformed coevolution in experiments, NEAT did develop an advanced mobility strategy. Also we demonstrated the need for protection of long-term strategies in coevolution. NEAT established its potential to enter the game playing arena and illustrated the necessity of the mobility strategy in defeating a powerful positional player in Othello.