Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration

Abstract : Intrinsically motivated goal exploration algorithms enable machines to discover repertoires of policies that produce a diversity of effects in complex environments. These exploration algorithms have been shown to allow real world robots to acquire skills such as tool use in high-dimensional continuous state and action spaces. However, they have so far assumed that self-generated goals are sampled in a specifically engineered feature space, limiting their autonomy. In this work, we propose to use deep representation learning algorithms to learn an adequate goal space. This is a developmental 2-stage approach: first, in a perceptual learning stage, deep learning algorithms use passive raw sensor observations of world changes to learn a corresponding latent space; then goal exploration happens in a second stage by sampling goals in this latent space. We present experiments where a simulated robot arm interacts with an object, and we show that exploration algorithms using such learned representations can match the performance obtained using engineered representations.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01891758
Contributor : Alexandre Péré <>
Submitted on : Tuesday, October 9, 2018 - 8:38:43 PM
Last modification on : Tuesday, March 26, 2019 - 1:28:52 AM

File

unsupervised-learning-goal(1)....
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01891758, version 1

Citation

Alexandre Péré, Sébastien Forestier, Olivier Sigaud, Pierre-Yves Oudeyer. Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration. ICLR2018 - 6th International Conference on Learning Representations, Apr 2018, Vancouver, Canada. ⟨hal-01891758⟩

Share

Metrics

Record views

80

Files downloads

41