Neural networks elitist evolution

This paper presents an elitist evolving strategy, which allows obtaining a controller, based on a neural network capable of commanding an autonomous robot. In order to reduce the detrimental crossover effect, we propose to use a strategy to create several children for each parent pair, selecting properly the way of making the replacement. The results obtained show that, though the number of children is high, the quantity of fitness tests carried out is actually lower than that of a conventional evolving algorithm. In this way, we propose an alternative that reduces the computational cost of the process, reaching at a suitable response for the problem resolution.