An empirical comparison of selection methods in evolutionary algorithms

Citation

Hancock PJB (1994) An empirical comparison of selection methods in evolutionary algorithms. In: Fogarty T (ed.) Evolutionary Computing: AISB Workshop Leeds, U.K., April 11–13, 1994 Selected Papers. Lecture Notes in Computer Science, 865. 1994 AISB Workshop, Leeds, 11.04.1994-13.04.1994. Berlin Heidelberg: Springer, pp. 80-94. http://link.springer.com/chapter/10.1007/3-540-58483-8_7#; https://doi.org/10.1007/3-540-58483-8_7

Abstract
Selection methods in Evolutionary Algorithms, including Genetic Algorithms, Evolution Strategies (ES) and Evolutionary Programming, (EP) are compared by observing the rate of convergence on three idealised problems. The first considers selection only, the second introduces mutation as a source of variation, the third also adds in evaluation noise. Fitness proportionate selection suffers from scaling problems: a number of techniques to reduce these are illustrated. The sampling errors caused by roulette wheel and tournament selection are demonstrated. The EP selection model is shown to be equivalent to an ES model in one form, and surprisingly similar to fitness proportionate selection in another. Generational models are shown to be remarkably immune to evaluation noise, models that retain parents much less so.

People

Professor Peter Hancock

Professor, Psychology