Learning to touch objects through stage-wise deep reinforcement learning - Archive ouverte HAL Access content directly
Conference Papers Year :

Learning to touch objects through stage-wise deep reinforcement learning

(1) , (1) , (2) , (1)
Céline Teulière
Thierry Chateau


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 (1.63 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01915423 , version 1 (15-01-2019)


  • HAL Id : hal-01915423 , version 1


François de La Bourdonnaye, Céline Teulière, Jochen Triesch, Thierry Chateau. Learning to touch objects through stage-wise deep reinforcement learning. IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2018, Madrid, Spain. ⟨hal-01915423⟩
63 View
145 Download


Gmail Facebook Twitter LinkedIn More