Importance Weighted Transfer of Samples in Reinforcement Learning

Tirinzoni, Andrea; Sessa, Andrea; Pirotta, Matteo; Restelli, Marcello

Type de document :

Communication dans un congrès avec actes

Titre :

Importance Weighted Transfer of Samples in Reinforcement Learning

Auteur(s) :

Tirinzoni, Andrea [Auteur]
Department of Electronics, Information, and Bioengineering [Milano] [DEIB]
Sessa, Andrea [Auteur]
Department of Electronics, Information, and Bioengineering [Milano] [DEIB]
Pirotta, Matteo [Auteur]
Sequential Learning [SEQUEL]
Restelli, Marcello [Auteur]
Department of Electronics, Information, and Bioengineering [Milano] [DEIB]

Titre de la manifestation scientifique :

ICML 2018 - The 35th International Conference on Machine Learning

Ville :

Stockholm

Pays :

Suède

Date de début de la manifestation scientifique :

2018-07-10

Titre de la revue :

Proceedings of Machine Learning Research

Discipline(s) HAL :

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

Résumé en anglais : [en]

We consider the transfer of experience samples (i.e., tuples < s, a, s', r >) in reinforcement learning (RL), collected from a set of source tasks to improve the learning process in a given target task. Most of the related ...
Lire la suite >We consider the transfer of experience samples (i.e., tuples < s, a, s', r >) in reinforcement learning (RL), collected from a set of source tasks to improve the learning process in a given target task. Most of the related approaches focus on selecting the most relevant source samples for solving the target task, but then all the transferred samples are used without considering anymore the discrepancies between the task models. In this paper, we propose a model-based technique that automatically estimates the relevance (importance weight) of each source sample for solving the target task. In the proposed approach, all the samples are transferred and used by a batch RL algorithm to solve the target task, but their contribution to the learning process is proportional to their importance weight. By extending the results for importance weighting provided in supervised learning literature, we develop a finite-sample analysis of the proposed batch RL algorithm. Furthermore, we empirically compare the proposed algorithm to state-of-the-art approaches, showing that it achieves better learning performance and is very robust to negative transfer, even when some source tasks are significantly different from the target task.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 :