42 citations · 57 across the 6 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.LG2020★ 13 cited
Latent World Models For Intrinsically Motivated Exploration
Aleksandr Ermolov, Nicu Sebe
In this work we consider partially observable environments with sparse rewards. We present a self-supervised representation learning method for image-based observations, which arra…
cs.LG2020★ 42 cited
Whitening for Self-Supervised Representation Learning
Aleksandr Ermolov, Aliaksandr Siarohin, Enver Sangineto +1
Most of the current self-supervised representation learning (SSL) methods are based on the contrastive loss and the instance-discrimination task, where augmented versions of the sa…