A step size based self-adaptive mutation operator for evolutionary programming

Abstract

The mutation operator is the only genetic operator in Evolutionary Programming (EP). In the past researchers have nominated Gaussian, Cauchy, and Levy distributions as mutation operators. According to the No Free Lunch theorem [9], no single mutation operator is able to outperform all others over the set of all possible functions. Potentially there is a lot of useful information generated when EP is ongoing. In this paper, we collect such information and propose a step size based self-adaptive mutation operator for Evolutionary Programming (SSEP). In SSEP, the mutation operator might be changed during the evolutionary process, based on the step size, from generation to generation. Principles for selecting an appropriate mutation operator for EP is proposed, with SSEP grounded on the principles. SSEP is shown to outperform static mutation operators in Evolutionary Programming on most of the functions tested. We also compare the experimental results of SSEP with other recent Evolutionary Programming methods, which uses multiple mutation operators.