Comparing reliability of grid-based Quality-Diversity algorithms using artificial landscapes

TL;DR

This paper introduces a benchmark using the Rastrigin function to evaluate and compare the reliability of grid-based Quality-Diversity algorithms in exploring artificial landscapes.

Contribution

It proposes a simple, standardized benchmark for assessing the reliability of QD algorithms, addressing the lack of reference benchmarks in the field.

Findings

Benchmark effectively differentiates algorithm reliability.

Grid-based QD algorithms show varying performance on the Rastrigin landscape.

Provides a basis for future comparative studies.

Abstract

Quality-Diversity (QD) algorithms are a recent type of optimisation methods that search for a collection of both diverse and high performing solutions. They can be used to effectively explore a target problem according to features defined by the user. However, the field of QD still does not possess extensive methodologies and reference benchmarks to compare these algorithms. We propose a simple benchmark to compare the reliability of QD algorithms by optimising the Rastrigin function, an artificial landscape function often used to test global optimisation methods.