Learning to touch objects through stage-wise deep reinforcement learning - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

Learning to touch objects through stage-wise deep reinforcement learning

Résumé

Learning complex behaviors through reinforcement learning is particularly challenging when reward is only available upon successful completion of the full behavior. In manipulation robotics, so-called shaping rewards are often used to overcome this problem. However, these usually require human engineering or (partial) world models describing, e.g., the kinematics of the robot or high-level modules for perception. Here we propose an alternative method to learn an object palm-touching task through a weakly-supervised and stage-wise learning of simpler tasks. First, the robot learns to fixate the object with its cameras. Second, the robot learns eye-hand coordination by learning to fixate its end effector. Third, using the previously acquired skills an informative shaping reward can be computed which facilitates efficient learning of the object palm-touching task. We demonstrate in simulation that learning the full task with this shaping reward is comparable to learning with an informative supervised reward.
Fichier principal
Vignette du fichier
fdlb_paper_iros_v1.pdf (1.46 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01820043 , version 1 (21-06-2018)

Identifiants

  • HAL Id : hal-01820043 , version 1

Citer

François de La Bourdonnaye, Céline Teulière, Jochen Triesch, Thierry Chateau. Learning to touch objects through stage-wise deep reinforcement learning. 2018. ⟨hal-01820043⟩
560 Consultations
570 Téléchargements

Partager

Gmail Facebook X LinkedIn More