City Research Online

Symmetry-Based Disentangled Representation Learning requires Interaction with Environments

Caselles-Dupré, H., Garcia Ortiz, M. ORCID: 0000-0003-4729-7457 and Filliat, D. (2019). Symmetry-Based Disentangled Representation Learning requires Interaction with Environments. Paper presented at the Thirty-third Conference on Neural Information Processing Systems (NeurIPS 2019), 8-14 Dec 2019, Vancouver, Canada.

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.

Publication Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Departments: School of Mathematics, Computer Science & Engineering > Computer Science
Date Deposited: 13 Sep 2019 11:15
URI: https://openaccess.city.ac.uk/id/eprint/22449
[img]
Preview
Text - Accepted Version
Download (919kB) | Preview

Export

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login