A Simple Haploid-Diploid Evolutionary Algorithm

TL;DR

This paper introduces a simple modification to evolutionary algorithms inspired by haploid-diploid cycles in eukaryotic sex, demonstrating improved performance on rugged fitness landscapes modeled by the NK model.

Contribution

It proposes a straightforward adjustment to standard evolutionary algorithms to leverage haploid-diploid cycling effects, enhancing search in complex landscapes.

Findings

Benefit increases with landscape ruggedness

Improved search efficiency on NK model landscapes

Simple modification yields notable performance gains

Abstract

It has recently been suggested that evolution exploits a form of fitness landscape smoothing within eukaryotic sex due to the haploid-diploid cycle. This short paper presents a simple modification to the standard evolutionary computing algorithm to similarly benefit from the process. Using the well-known NK model of fitness landscapes it is shown that the benefit emerges as ruggedness is increased.