Confronting The Challenge Of Quality Diversity

Keywords

Neuroevolution; Non-objective search; Novelty search; Quality diversity

Abstract

In contrast to the conventional role of evolution in evolutionary computation (EC) as an optimization algorithm, a new class of evolutionary algorithms has emerged in recent years that instead aim to accumulate as diverse a collection of discoveries as possible, yet where each variant in the collection is as fit as it can be. Often applied in both neuroevolution and morphological evolution, these new quality diversity (QD) algorithms are particularly well-suited to evolution's inherent strengths, thereby offering a promising niche for EC within the broader field of machine learning. However, because QD algorithms are so new, until now no comprehensive study has yet attempted to systematically elucidate their relative strengths and weaknesses under different conditions. Taking a first step in this direction, this paper introduces a new benchmark domain designed specifically to compare and contrast QD algorithms. It then shows how the degree of alignment between the measure of quality and the behavior characterization (which is an essential component of all QD algorithms to date) impacts the ultimate performance of different such algorithms. The hope is that this initial study will help to stimulate interest in QD and begin to unify the disparate ideas in the area.

Publication Date

7-11-2015

Publication Title

GECCO 2015 - Proceedings of the 2015 Genetic and Evolutionary Computation Conference

Number of Pages

967-974

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1145/2739480.2754664

Socpus ID

84963680451 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/84963680451

This document is currently not available here.

Share

COinS