Progress Rate in Noisy Genetic Programming for Choosing λ
Résumé
Recently, it has been proposed to use Bernstein races for implementing non-regression testing in noisy genetic programming. We study the population size of such a (1+λ) evolutionary algorithm applied to a noisy fitness function optimization by a progress rate analysis and experiment it on a policy search application.
Origine | Fichiers produits par l'(les) auteur(s) |
---|
Loading...