English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Finding a generally accepted formal definition of a disentangledrepresentation in the context of an agent behaving in an environment is animportant challenge towards the construction of data-efficient autonomousagents. Higgins et al. recently proposed Symmetry-Based DisentangledRepresentation Learning, a definition based on a characterization of symmetriesin the environment using group theory. We build on their work and makeobservations, theoretical and empirical, that lead us to argue thatSymmetry-Based Disentangled Representation Learning cannot only be based onstatic observations: agents should interact with the environment to discoverits symmetries. Our experiments can be reproduced in Colab and the code isavailable on GitHub.

Symmetry-Based Disentangled Representation Learning requires Interaction with Environments