Diversity-driven selection of exploration strategies in multi-armed bandits

Fabien Benureau 1, * Pierre-Yves Oudeyer 1
* Auteur correspondant
1 Flowers - Flowing Epigenetic Robots and Systems
Inria Bordeaux - Sud-Ouest, U2IS - Unité d'Informatique et d'Ingénierie des Systèmes
Abstract : We consider a scenario where an agent has multiple available strategies to explore an unknown environment. For each new interaction with the environment, the agent must select which exploration strategy to use. We provide a new strategy-agnostic method that treat the situation as a Multi-Armed Bandits problem where the reward signal is the diversity of effects that each strategy produces. We test the method empirically on a simulated planar robotic arm, and establish that the method is both able discriminate between strategies of dissimilar quality, even when the differences are tenuous, and that the resulting performance is competitive with the best fixed mixture of strategies.
Type de document :
Communication dans un congrès
IEEE International Conference on Development and Learning and Epigenetic Robotics, Aug 2015, Providence, United States. 2015, Proceedings of IEEE International Conference on Development and Learning and Epigenetic Robotics. 〈10.1109/DEVLRN.2015.7346130〉
Liste complète des métadonnées

Littérature citée [36 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01251060
Contributeur : Pierre-Yves Oudeyer <>
Soumis le : mardi 5 janvier 2016 - 15:38:24
Dernière modification le : jeudi 12 avril 2018 - 14:17:55
Document(s) archivé(s) le : jeudi 7 avril 2016 - 15:28:44

Fichier

BenureauOudeyerIcdl2015.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Fabien Benureau, Pierre-Yves Oudeyer. Diversity-driven selection of exploration strategies in multi-armed bandits. IEEE International Conference on Development and Learning and Epigenetic Robotics, Aug 2015, Providence, United States. 2015, Proceedings of IEEE International Conference on Development and Learning and Epigenetic Robotics. 〈10.1109/DEVLRN.2015.7346130〉. 〈hal-01251060〉

Partager

Métriques

Consultations de la notice

150

Téléchargements de fichiers

178