A comparison of illumination algorithms in unbounded spaces

Vassilis Vassiliades 1 Konstantinos Chatzilygeroudis 1 Jean-Baptiste Mouret 1
1 LARSEN - Lifelong Autonomy and interaction skills for Robots in a Sensing ENvironment
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : Illumination algorithms are a new class of evolutionary algorithms capable of producing large archives of diverse and high-performing solutions. Examples of such algorithms include Novelty Search with Local Competition (NSLC), the Multi-dimensional Archive of Phenotypic Elites (MAP-Elites) and the newly introduced Cen-troidal Voronoi Tessellation (CVT) MAP-Elites. While NSLC can be used in unbounded behavioral spaces, MAP-Elites and CVT-MAP-Elites require the user to manually specify the bounds. In this study, we introduce variants of these algorithms that expand their bounds based on the discovered solutions. In addition, we introduce a novel algorithm called "Cluster-Elites" that can adapt its bounds to non-convex spaces. We compare all algorithms in a maze navigation problem and illustrate that Cluster-Elites and the expansive variants of MAP-Elites and CVT-MAP-Elites have comparable or better performance than NSLC, MAP-Elites and CVT-MAP-Elites.
Type de document :
Communication dans un congrès
Workshop "Measuring and Promoting Diversity in Evolutionary Algorithms", Genetic and Evolutionary Computation Conference, 2017, Berlin, Germany. Proceedings of The Genetic and Evolutionary Computation Conference Companion 2017
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01518814
Contributeur : Jean-Baptiste Mouret <>
Soumis le : vendredi 5 mai 2017 - 14:39:44
Dernière modification le : jeudi 11 janvier 2018 - 06:27:29
Document(s) archivé(s) le : dimanche 6 août 2017 - 15:11:24

Fichier

2017_vassiliades_gecco_unbound...
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01518814, version 1

Citation

Vassilis Vassiliades, Konstantinos Chatzilygeroudis, Jean-Baptiste Mouret. A comparison of illumination algorithms in unbounded spaces. Workshop "Measuring and Promoting Diversity in Evolutionary Algorithms", Genetic and Evolutionary Computation Conference, 2017, Berlin, Germany. Proceedings of The Genetic and Evolutionary Computation Conference Companion 2017. 〈hal-01518814〉

Partager

Métriques

Consultations de la notice

302

Téléchargements de fichiers

144