Robot Manipulation Learning Using Generative Adversarial Imitation Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Robot Manipulation Learning Using Generative Adversarial Imitation Learning

Résumé

Imitation learning allows learning complex behaviors given demonstrations. Early approaches belonging to either Behavior Cloning or Inverse Reinforcement Learning were however of limited scalability to complex environments. A more promising approach termed as Generative Adversarial Imitation Learning tackles the imitation learning problem by drawing a connection with Generative Adversarial Networks. In this work, we advocate the use of this class of methods and investigate possible extensions by endowing them with global temporal consistency, in particular through a contrastive learning based approach.
Fichier principal
Vignette du fichier
IJCAI__DC(1).pdf (177.31 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03352265 , version 1 (23-09-2021)

Identifiants

Citer

Mohamed Khalil Jabri. Robot Manipulation Learning Using Generative Adversarial Imitation Learning. Thirtieth International Joint Conference on Artificial Intelligence, Aug 2021, Montreal (virtual), Canada. pp.4893-4894, ⟨10.24963/ijcai.2021/678⟩. ⟨hal-03352265⟩
229 Consultations
133 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More