Sparse Multi-task Reinforcement Learning

Calandriello, Daniele; Lazaric, Alessandro; Restelli, Marcello

Document type :

Communication dans un congrès avec actes

Title :

Sparse Multi-task Reinforcement Learning

Author(s) :

Calandriello, Daniele [Auteur]
Laboratoire d'Informatique Fondamentale de Lille [LIFL]
Sequential Learning [SEQUEL]
Lazaric, Alessandro [Auteur]

Laboratoire d'Informatique Fondamentale de Lille [LIFL]
Sequential Learning [SEQUEL]
Restelli, Marcello [Auteur]

Conference title :

NIPS - Advances in Neural Information Processing Systems 26

City :

Montreal

Country :

Canada

Start date of the conference :

2014-12

Publication date :

2014

HAL domain(s) :

Statistiques [stat]/Machine Learning [stat.ML]

English abstract : [en]

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 ...
Show more >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.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

ANR Project :

Extraction et transfert de connaissances dans l'apprentissage par renforcement

Collections :