A Genetic Algorithm With Self-Generated Random Parameters

Sonja Novkovic, Davor Sverko

Abstract


In this paper we present a version of genetic algorithm (GA) where parameters are created by the GA itself, rather than predetermined by the programmer. Chromosome portions which do not translate into fitness (“genetic residual”) are given function to diversify control parameters for the GA,providing random parameter setting along the way, and doing away with fine-tuning of probabilities of crossover and mutation. We test the algorithm on Royal Road functions to examine the difference between our version (GAR) and the simple genetic algorithm (SGA) in the speed of discovering schema and creating building blocks. We also look at the usefulness of other standard improvements, such as non-coding segments, elitist selection and multiple crossover on the evolution of schema.

Full Text:

PDF


DOI: https://doi.org/10.2498/cit.2003.04.02

Creative Commons License
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.

Crossref Similarity Check logo

Crossref logologo_doaj