Transfer Reinforcement Learning with Shared Dynamics

Laroche, Romain; Barlier, Merwan

Document type :

Communication dans un congrès avec actes

Title :

Transfer Reinforcement Learning with Shared Dynamics

Author(s) :

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

Conference title :

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

City :

San Francisco

Country :

Etats-Unis d'Amérique

Start date of the conference :

2017-02-04

Publication date :

2017-02-13

HAL domain(s) :

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

English abstract : [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 ...
Show more >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.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

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

Source :

Harvested from HAL

Files

https://hal.archives-ouvertes.fr/hal-01548649/document
Open access
Access the document

https://hal.archives-ouvertes.fr/hal-01548649/document
Open access
Access the document

https://hal.archives-ouvertes.fr/hal-01548649/document
Open access
Access the document

document
Open access
Access the document

aaai-multi-task%281%29.pdf
Open access
Access the document

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

Files

Transfer Reinforcement Learning with Shared ...

BibTeX

CSV

Excel

RIS