Keywords: Representation Learning, Interaction, Equivariance
TL;DR: We propose a representation learning framework that extracts from observations the geometric state of both an agent and an object the agent interacts with.
Abstract: We address the problem of learning geometric representations from observations perceived by an agent operating within an environment and interacting with an external object. To this end, we propose a representation learning framework that extracts the state of both the agent and the object from unstructured observations of arbitrary nature (e.g., images). Supervision comes from the performed actions alone, while the dynamics of the object is assumed to be unknown. We provide a theoretical foundation and formally prove that an ideal learner is guaranteed to infer an isometric representation, disentangling the agent from the object. Finally, we investigate empirically our framework on a variety of scenarios. Results show that our model reliably infers the correct representation and outperforms vision-based approaches such as a state-of-the-art keypoint extractor.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Submission Guidelines: Yes
Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning