Co-evolution, Determinism and Robustness

Robustness has long been recognised as a critical issue for coevolutionary learning. It has been achieved in a number of cases, though usually in domains which involve some form of non-determinism. We examine a deterministic domain - a pseudo real-time two-player game called Tron - and evolve a neural network player using a simple hill-climbing algorithm. The results call into question the importance of determinism as a requirement for successful co-evolutionary learning, and provide a good opportunity to examine the relative importance of other factors.