Haploid-Diploid Evolutionary Algorithms

TL;DR

This paper introduces a novel evolutionary algorithm inspired by haploid-diploid lifecycles, viewing recombination as a form of learning, and demonstrates its effectiveness across different fitness landscape ruggedness levels.

Contribution

It presents a new haploid-diploid based evolutionary computation method that differs from traditional diploid representations and redefines the role of recombination.

Findings

Varying landscape ruggedness affects the benefits of the new approach.

The method shows improved performance on certain fitness landscapes.

Recombination acts as a learning mechanism in the new model.

Abstract

This paper uses the recent idea that the fundamental haploid-diploid lifecycle of eukaryotic organisms implements a rudimentary form of learning within evolution. A general approach for evolutionary computation is here derived that differs from all previous known work using diploid representations. The primary role of recombination is also changed from that previously considered in both natural and artificial evolution under the new view. Using well-known abstract tuneable models it is shown that varying fitness landscape ruggedness varies the benefit of the new approach.