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. 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.
Cite
@article{arxiv.1904.00243,
title = {Symmetry-Based Disentangled Representation Learning requires Interaction with Environments},
author = {Hugo Caselles-Dupré and Michael Garcia-Ortiz and David Filliat},
journal= {arXiv preprint arXiv:1904.00243},
year = {2019}
}
Comments
33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada