A Fitted-Q Algorithm for Budgeted MDPs
Type de document :
Communication dans un congrès avec actes
Titre :
A Fitted-Q Algorithm for Budgeted MDPs
Auteur(s) :
Carrara, Nicolas [Auteur]
Orange Labs [Lannion]
Sequential Learning [SEQUEL]
Laroche, Romain [Auteur]
Maluuba
Bouraoui, Jean-Léon [Auteur]
Orange Labs [Lannion]
Urvoy, Tanguy [Auteur]
Orange Labs [Lannion]
Pietquin, Olivier [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Orange Labs [Lannion]
Sequential Learning [SEQUEL]
Laroche, Romain [Auteur]
Maluuba
Bouraoui, Jean-Léon [Auteur]
Orange Labs [Lannion]
Urvoy, Tanguy [Auteur]
Orange Labs [Lannion]
Pietquin, Olivier [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Titre de la manifestation scientifique :
EWRL 2018 - 14th European workshop on Reinforcement Learning
Ville :
Lille
Pays :
France
Date de début de la manifestation scientifique :
2018-10-01
Date de publication :
2018
Mot(s)-clé(s) en anglais :
Budgeted-MDP
Fitted-Q
Reinforcement Learning
Fitted-Q
Reinforcement Learning
Discipline(s) HAL :
Informatique [cs]/Intelligence artificielle [cs.AI]
Résumé en anglais : [en]
We address the problem of budgeted reinforcement learning, in continuous state-space, using a batch of transitions. To this extend, we introduce a novel algorithm called Budgeted Fitted-Q (BFTQ). Benchmarks show that BFTQ ...
Lire la suite >We address the problem of budgeted reinforcement learning, in continuous state-space, using a batch of transitions. To this extend, we introduce a novel algorithm called Budgeted Fitted-Q (BFTQ). Benchmarks show that BFTQ performs as well as a regular Fitted-Q algorithm in a continuous 2-D world but also allows one to choose the right amount of budget that fits to a given task without the need of engineering the rewards. We believe that the general principles used to design BFTQ can be applied to extend others classical reinforcement learning algorithms for budgeted oriented applications.Lire moins >
Lire la suite >We address the problem of budgeted reinforcement learning, in continuous state-space, using a batch of transitions. To this extend, we introduce a novel algorithm called Budgeted Fitted-Q (BFTQ). Benchmarks show that BFTQ performs as well as a regular Fitted-Q algorithm in a continuous 2-D world but also allows one to choose the right amount of budget that fits to a given task without the need of engineering the rewards. We believe that the general principles used to design BFTQ can be applied to extend others classical reinforcement learning algorithms for budgeted oriented applications.Lire moins >
Langue :
Anglais
Comité de lecture :
Oui
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Fichiers
- https://hal.archives-ouvertes.fr/hal-01928092/document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-01928092/document
- Accès libre
- Accéder au document
- https://hal.archives-ouvertes.fr/hal-01928092/document
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- ewrl_14_2018_paper_67.pdf
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- ewrl_14_2018_paper_67.pdf
- Accès libre
- Accéder au document