-
COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration
Data efficiency and robustness to task-irrelevant perturbations are long...
05/22/2019 ∙ by Nicholas Watters, et al. ∙
12
∙
share
read it
-
Visual Interaction Networks
From just a glance, humans can make rich predictions about the future st...
06/05/2017 ∙ by Nicholas Watters, et al. ∙
0
∙
share
read it
-
Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
We present a simple neural rendering architecture that helps variational...
01/21/2019 ∙ by Nicholas Watters, et al. ∙
0
∙
share
read it
-
MONet: Unsupervised Scene Decomposition and Representation
The ability to decompose scenes in terms of abstract building blocks is ...
01/22/2019 ∙ by Christopher P Burgess, et al. ∙
0
∙
share
read it
-
A Heuristic for Unsupervised Model Selection for Variational Disentangled Representation Learning
Disentangled representations have recently been shown to improve data ef...
05/29/2019 ∙ by Sunny Duan, et al. ∙
0
∙
share
read it
