Decentralized Innovation Marking for Neural Controllers in Embodied Evolution

Iñaki Fernández Pérez 1, 2 Amine Boumaza 2, 1 François Charpillet 3
2 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 : We propose a novel innovation marking method for Neuro-Evolution of Augmenting Topologies in Embodied Evolutionary Robotics. This method does not rely on a centralized clock, which makes it well suited for the decentralized nature of EE where no central evolutionary process governs the adaptation of a team of robots exchanging messages locally. This method is inspired from event dating algorithms, based on logical clocks, that are used in distributed systems, where clock synchronization is not possible. We compare our method to odNEAT, an algorithm in which agents use local time clocks as innovation numbers, on two multi-robot learning tasks: navigation and item collection. Our experiments showed that the proposed method performs as well as odNEAT, with the added benefit that it does not rely on synchronization of clocks and is not affected by time drifts.
Type de document :
Communication dans un congrès
GECCO '15, 2015 Annual Conference on Genetic and Evolutionary Computation, Jul 2015, Madrid, Spain. GECCO '15 Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation, 2015, 〈10.1145/2739480.2754759〉
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01212761
Contributeur : Iñaki Fernandez <>
Soumis le : jeudi 8 octobre 2015 - 09:31:38
Dernière modification le : jeudi 11 janvier 2018 - 06:27:29
Document(s) archivé(s) le : samedi 9 janvier 2016 - 10:13:21

Fichier

tweannNoFormat.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Iñaki Fernández Pérez, Amine Boumaza, François Charpillet. Decentralized Innovation Marking for Neural Controllers in Embodied Evolution. GECCO '15, 2015 Annual Conference on Genetic and Evolutionary Computation, Jul 2015, Madrid, Spain. GECCO '15 Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation, 2015, 〈10.1145/2739480.2754759〉. 〈hal-01212761〉

Partager

Métriques

Consultations de la notice

182

Téléchargements de fichiers

81