Titre :

Only Relevant Information Matters: Filtering Out Noisy Samples to Boost RL

Auteur(s) :

Flet Berliac, Yannis [Auteur]
Scool [Scool]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Sequential Learning [SEQUEL]
Preux, Philippe [Auteur]
Scool [Scool]
Sequential Learning [SEQUEL]

Titre de la manifestation scientifique :

IJCAI 2020 - International Joint Conference on Artificial Intelligence

Ville :

Yokohama

Pays :

Japon

Date de début de la manifestation scientifique :

2020-07-11

Mot(s)-clé(s) en anglais :

reinforcement learning
sampling
policy gradient

Discipline(s) HAL :

Informatique [cs]/Apprentissage [cs.LG]
Statistiques [stat]/Machine Learning [stat.ML]
Informatique [cs]/Intelligence artificielle [cs.AI]

Résumé en anglais : [en]

In reinforcement learning, policy gradient algorithms optimize the policy directly and rely on sampling efficiently an environment. Nevertheless, while most sampling procedures are based on direct policy sampling, ...
Lire la suite >In reinforcement learning, policy gradient algorithms optimize the policy directly and rely on sampling efficiently an environment. Nevertheless, while most sampling procedures are based on direct policy sampling, self-performance measures could be used to improve such sampling prior to each policy update. Following this line of thought, we introduce SAUNA, a method where non-informative transitions are rejected from the gradient update. The level of information is estimated according to the fraction of variance explained by the value function: a measure of the discrepancy between V and the empirical returns. In this work, we use this metric to select samples that are useful to learn from, and we demonstrate that this selection can significantly improve the performance of policy gradient methods. In this paper: (a) We define SAUNA's metric and introduce its method to filter transitions. (b) We conduct experiments on a set of benchmark continuous control problems. SAUNA significantly improves performance. (c) We investigate how SAUNA reliably selects samples with the most positive impact on learning and study its improvement on both performance and sample efficiency.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