Sparse Multi-task Reinforcement Learning

Daniele Calandriello 1, 2 Alessandro Lazaric 1, 2 Marcello Restelli 3
1 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : In multi-task reinforcement learning (MTRL), the objective is to simultaneously learn multiple tasks and exploit their similarity to improve the performance w.r.t.\ single-task learning. In this paper we investigate the case when all the tasks can be accurately represented in a linear approximation space using the same small subset of the original (large) set of features. This is equivalent to assuming that the weight vectors of the task value functions are \textit{jointly sparse}, i.e., the set of their non-zero components is small and it is shared across tasks. Building on existing results in multi-task regression, we develop two multi-task extensions of the fitted $Q$-iteration algorithm. While the first algorithm assumes that the tasks are jointly sparse in the given representation, the second one learns a transformation of the features in the attempt of finding a more sparse representation. For both algorithms we provide a sample complexity analysis and numerical simulations.
Type de document :
Communication dans un congrès
NIPS - Advances in Neural Information Processing Systems 26, Dec 2014, Montreal, Canada. 2014
Liste complète des métadonnées

Littérature citée [31 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01073513
Contributeur : Alessandro Lazaric <>
Soumis le : samedi 31 janvier 2015 - 15:30:37
Dernière modification le : jeudi 11 janvier 2018 - 06:22:13
Document(s) archivé(s) le : mercredi 27 mai 2015 - 15:10:36

Fichier

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

Identifiants

  • HAL Id : hal-01073513, version 1

Citation

Daniele Calandriello, Alessandro Lazaric, Marcello Restelli. Sparse Multi-task Reinforcement Learning. NIPS - Advances in Neural Information Processing Systems 26, Dec 2014, Montreal, Canada. 2014. 〈hal-01073513〉

Partager

Métriques

Consultations de la notice

315

Téléchargements de fichiers

208