Transfer Reinforcement Learning with Shared Dynamics

Laroche, Romain; Barlier, Merwan

Type de document :

Communication dans un congrès avec actes

Titre :

Transfer Reinforcement Learning with Shared Dynamics

Auteur(s) :

Laroche, Romain [Auteur]
Orange Labs [Issy les Moulineaux]
Barlier, Merwan [Auteur]
Sequential Learning [SEQUEL]
Orange Labs [Issy les Moulineaux]

Titre de la manifestation scientifique :

AAAI-17 - Thirty-First AAAI Conference on Artificial Intelligence

Ville :

San Francisco

Pays :

Etats-Unis d'Amérique

Date de début de la manifestation scientifique :

2017-02-04

Date de publication :

2017-02-13

Discipline(s) HAL :

Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Apprentissage [cs.LG]

Résumé en anglais : [en]

This article addresses a particular Transfer Reinforcement Learning (RL) problem: when dynamics do not change from one task to another, and only the reward function does. Our method relies on two ideas, the first one is ...
Lire la suite >This article addresses a particular Transfer Reinforcement Learning (RL) problem: when dynamics do not change from one task to another, and only the reward function does. Our method relies on two ideas, the first one is that transition samples obtained from a task can be reused to learn on any other task: an immediate reward estimator is learnt in a supervised fashion and for each sample, the reward entry is changed by its reward estimate. The second idea consists in adopting the optimism in the face of uncertainty principle and to use upper bound reward estimates. Our method is tested on a navigation task, under four Transfer RL experimental settings: with a known reward function, with strong and weak expert knowledge on the reward function, and with a completely unknown reward function. It is also evaluated in a Multi-Task RL experiment and compared with the state-of-the-art algorithms. Results reveal that this method constitutes a major improvement for transfer/multi-task problems that share dynamics.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Collections :

Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL

Fichiers

https://hal.archives-ouvertes.fr/hal-01548649/document
Accès libre
Accéder au document

https://hal.archives-ouvertes.fr/hal-01548649/document
Accès libre
Accéder au document

https://hal.archives-ouvertes.fr/hal-01548649/document
Accès libre
Accéder au document

document
Accès libre
Accéder au document

aaai-multi-task%281%29.pdf
Accès libre
Accéder au document

document
Accès libre
Accéder au document

aaai-multi-task%281%29.pdf
Accès libre
Accéder au document

Transfer Reinforcement Learning with Shared ... BibTeX CSV Excel RIS

Fichiers

Transfer Reinforcement Learning with Shared ...

BibTeX

CSV

Excel

RIS