Direct Policy Iteration with Demonstrations

Chemali, Jessica; Lazaric, Alessandro

Type de document :

Communication dans un congrès avec actes

Titre :

Direct Policy Iteration with Demonstrations

Auteur(s) :

Chemali, Jessica [Auteur]
Computer Science Department - Carnegie Mellon University
Lazaric, Alessandro [Auteur]

Sequential Learning [SEQUEL]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]

Titre de la manifestation scientifique :

IJCAI - 24th International Joint Conference on Artificial Intelligence

Ville :

Buenos Aires

Pays :

Argentine

Date de début de la manifestation scientifique :

2015-07-25

Date de publication :

2015-07

Discipline(s) HAL :

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

Résumé en anglais : [en]

We consider the problem of learning the optimal policy of an unknown Markov decision process (MDP) when expert demonstrations are available along with interaction samples. We build on classification-based policy iteration ...
Lire la suite >We consider the problem of learning the optimal policy of an unknown Markov decision process (MDP) when expert demonstrations are available along with interaction samples. We build on classification-based policy iteration to perform a seamless integration of interaction and expert data, thus obtaining an algorithm which can benefit from both sources of information at the same time. Furthermore , we provide a full theoretical analysis of the performance across iterations providing insights on how the algorithm works. Finally, we report an empirical evaluation of the algorithm and a comparison with the state-of-the-art algorithms.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Projet ANR :

Extraction et transfert de connaissances dans l'apprentissage par renforcement

Collections :