This repository contains the official code for the NeurIPS 2019 paper "Symmetry-Based Disentangled Representation Learning requires Interaction with Environments" by Hugo Caselles-Dupré, Michael Garcia-Ortiz and David Filliat.
Symmetry-Based Disentangled Representation Learning requires Interaction with Environments
Hugo Caselles-Dupré ¹ ², Michael Garcia-Ortiz ² and David Filliat ¹
¹ Flowers Laboratory (ENSTA Paris& INRIA
)
² Softbank Robotics Europe
https://arxiv.org/abs/1904.00243Abstract: 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 fixed data samples. Agents should interact with the environment to discover its symmetries.
Open Colab Notebook to reproduce paper's experiments.
All material related to our paper is available via the following links:
| Link | Description |
|---|---|
| Link ArXiv | Paper PDF. |
| Link Project Page | Project page. |
| Link Video | Summary video. |
| Link Colab | Colab to reproduce experiments. |
| Link Github | Source code. |
| Link Slides | Presentation slides. |
| Link Poster | Poster. |