Curiosity Driven Exploration of Learned Disentangled Goal Spaces - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

Curiosity Driven Exploration of Learned Disentangled Goal Spaces

Adrien Laversanne-Finot
  • Function : Author
  • PersonId : 1037304
Alexandre Péré
  • Function : Author
  • PersonId : 1037305
Pierre-Yves Oudeyer


Intrinsically motivated goal exploration processes enable agents to autonomously sample goals to explore efficiently complex environments with high-dimensional continuous actions. They have been applied successfully to real world robots to discover repertoires of policies producing a wide diversity of effects. Often these algorithms relied on engineered goal spaces but it was recently shown that one can use deep representation learning algorithms to learn an adequate goal space in simple environments. However, in the case of more complex environments containing multiple objects or distractors, an efficient exploration requires that the structure of the goal space reflects the one of the environment. In this paper we show that using a disentangled goal space leads to better exploration performances than an entangled goal space. We further show that when the representation is disentangled, one can leverage it by sampling goals that maximize learning progress in a modular manner. Finally, we show that the measure of learning progress, used to drive curiosity-driven exploration, can be used simultaneously to discover abstract independently controllable features of the environment. The code used in the experiments is available at Curiosity_Driven_Goal_Exploration.
Fichier principal
Vignette du fichier
1807.01521.pdf (6.54 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01891598 , version 1 (09-10-2018)


  • HAL Id : hal-01891598 , version 1


Adrien Laversanne-Finot, Alexandre Péré, Pierre-Yves Oudeyer. Curiosity Driven Exploration of Learned Disentangled Goal Spaces. CoRL 2018 - Conference on Robot Learning, Oct 2018, Zürich, Switzerland. ⟨hal-01891598⟩
268 View
511 Download


Gmail Facebook X LinkedIn More