Reward-Based Environment States for Robot Manipulation Policy Learning - Université Toulouse III - Paul Sabatier - Toulouse INP Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Reward-Based Environment States for Robot Manipulation Policy Learning

Résumé

Training robot manipulation policies is a challenging and open problem in robotics and artificial intelligence. In this paper we propose a novel and compact state representation based on the rewards predicted from an image-based task success classifier. Our experiments—using the Pepper robot in simulation with two deep reinforcement learning algorithms on a grab-and-lift task—reveal that our proposed state representation can achieve up to 97% task success using our best policies.
Fichier principal
Vignette du fichier
NeurIPS2021_CR_final.pdf (291.34 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03631670 , version 1 (05-04-2022)

Identifiants

  • HAL Id : hal-03631670 , version 1

Citer

Cédérick Mouliets, Isabelle Ferrané, Heriberto Cuayáhuitl. Reward-Based Environment States for Robot Manipulation Policy Learning. NeurIPS Workshop on Deployable Decision Making in Embodied Systems (DDM 2021), University of Toronto, Dec 2021, Toronto, Canada. pp.1-6. ⟨hal-03631670⟩
30 Consultations
26 Téléchargements

Partager

Gmail Facebook X LinkedIn More