Discrete Gene Crossover Accelerates Solution Discovery in Quality-Diversity Algorithms

TL;DR

This paper introduces a gene-level crossover mutation operator for Quality-Diversity algorithms, inspired by biological meiosis, which enhances exploration and accelerates solution discovery in complex search spaces.

Contribution

It proposes a novel discrete gene crossover operator that improves the propagation of genetic material and exploration capabilities in QD algorithms, outperforming traditional mutation methods.

Findings

Improved QD score, coverage, and max fitness in locomotion tasks

Enhanced exploration and solution diversity in later optimization stages

Faster discovery of high-quality, diverse solutions

Abstract

Quality-Diversity (QD) algorithms aim to discover diverse, high-performing solutions across behavioral niches. However, QD search often stagnates as incremental variation operators struggle to propagate building blocks across large populations. Existing mutation operators rely on gradual variation to solutions, limiting their ability to efficiently explore regions of the search space distant from parent solutions or to spread beneficial genetic material through the population. We propose a mutation operator which augments variation-based operators with discrete, gene-level crossover, enabling rapid recombination of elite genetic material. This crossover mechanism mirrors the biological principle of meiosis and facilitates both the direct transfer of genetic material and the exploration of novel genotype configurations beyond the existing elite hypervolume. We evaluate operators on three locomotion environments, demonstrating improvements in QD score, coverage, and max fitness, with particularly strong performance in later stages of optimization once building blocks have been established in the archive. These results show that the addition of a discrete crossover mutation provides a complementary exploration mechanism that sustains quality-diversity growth beyond the performance demonstrated by existing operators.