Does Extra Genetic Diversity Maintain Escalation in a Co-Evolutionary Arms Race

In evolutionary computation (EC), genetic diversity (or its absence) gets the credit (or the blame) for a multitude of effects — and so mutation operators, population initialization, and even pseudo-random number generators, all get probed and prodded to improve genetic diversity. This paper demonstrates how extra initial diversity can appear to cause improvements in the performance of coevolutionary learning, but the true cause is in unforeseen effects of the problem-specific representation. The learning task considered in this paper is a variation on the game of Iterated Prisoner’s Dilemma (IPD): here players have a fine-grained range of intermediate choices between full cooperation and full defection.