Symmetry-Based Disentangled Representation Learning requires Interaction with Environments - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

Symmetry-Based Disentangled Representation Learning requires Interaction with Environments

Abstract

Finding a generally accepted formal definition of a disentangled representation in the context of an agent behaving in an environment is an important challenge towards the construction of data-efficient autonomous agents. Higgins et al. (2018) recently proposed Symmetry-Based Disentangled Representation Learning, a definition based on a characterization of symmetries in the environment using group theory. We build on their work and make observations, theoretical and empirical, that lead us to argue that Symmetry-Based Disentangled Representation Learning cannot only be based on static observations: agents should interact with the environment to discover its symmetries. Our experiments can be reproduced in Colab and the code is available on GitHub.
Fichier principal
Vignette du fichier
1904.00243.pdf (1001.06 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02379399 , version 1 (25-11-2019)

Identifiers

Cite

Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat. Symmetry-Based Disentangled Representation Learning requires Interaction with Environments. NeurIPS 2019 6 Neural Information Processing Conference, Dec 2019, Vancouver, Canada. ⟨hal-02379399⟩
94 View
54 Download

Altmetric

Share

Gmail Facebook X LinkedIn More