On the Importance of Distraction-Robust Representations for Robot Learning

Andy Wang, Antoine Cully

Keywords: Unsupervised Representation Learning, Robot Control, Quality-Diversity

Abstract:

Representation Learning methods can allow the application of Reinforcement Learning algorithms when a high dimensionality in a robot's perceptions would otherwise prove prohibitive. Consequently, unsupervised Representation Learning components often feature in robot control algorithms that assume high-dimensional camera images as the principal source of information.
In their design and performance, these algorithms often benefit from the controlled nature of the simulation or laboratory conditions they are evaluated in. However, these settings fail to acknowledge the stochasticity of most real-world environments.
In this work, we introduce the concept of Distraction-Robust Representation Learning. We argue that environment noise and other distractions require learned representations to encode the robot's expected perceptions rather than the observed ones. Our experimental evaluations demonstrate that representations learned with a traditional dimensionality reduction algorithm are strongly susceptible to distractions in a robot's environment.
We propose an Encoder-Decoder architecture that produces representations that allow the learning outcomes of robot control tasks to remain unaffected by these distractions.

One-sentence Summary: This paper introduces the concept of Distraction-Robust Representation Learning and proposes a simple and effective architecture that can be applied to robot learning algorithms.

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

Reviewed Version (pdf): https://openreview.net/references/pdf?id=Dej0iqOz_O