Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

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.
Fichier principal
Vignette du fichier
unsupervised-learning-goal(1).pdf (841.14 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01891758 , version 1 (09-10-2018)

Identifiers

  • HAL Id : hal-01891758 , version 1

Cite

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⟩
119 View
391 Download

Share

Gmail Facebook X LinkedIn More