Symmetry-Based Disentangled Representation Learning requires Interaction with Environments
Hugo Caselles-Dupré, Michael Garcia Ortiz, David Filliat
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. 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.
BibTeX
@inproceedings{NEURIPS2019_36e729ec,
author = {Caselles-Dupr\'{e}, Hugo and Garcia Ortiz, Michael and Filliat, David},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {Symmetry-Based Disentangled Representation Learning requires Interaction with Environments},
url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/36e729ec173b94133d8fa552e4029f8b-Paper.pdf},
volume = {32},
year = {2019}
}