59 citations · 180 across the 6 of their papers we have counts for
12 papers
Exploring through Random Curiosity with General Value Functions
Aditya Ramesh, Louis Kirsch, Sjoerd van Steenkiste +1
Efficient exploration in reinforcement learning is a challenging problem commonly addressed through intrinsic rewards. Recent prominent approaches are based on state novelty or var…
On the Binding Problem in Artificial Neural Networks
Klaus Greff, Sjoerd van Steenkiste, Jürgen Schmidhuber
Contemporary neural networks still fall short of human-level generalization, which extends far beyond our direct experiences. In this paper, we argue that the underlying cause for…
Unsupervised Object Keypoint Learning using Local Spatial Predictability
Anand Gopalakrishnan, Sjoerd van Steenkiste, Jürgen Schmidhuber
We propose PermaKey, a novel approach to representation learning based on object keypoints. It leverages the predictability of local image regions from spatial neighborhoods to ide…
Hierarchical Relational Inference
Aleksandar Stanić, Sjoerd van Steenkiste, Jürgen Schmidhuber
Common-sense physical reasoning in the real world requires learning about the interactions of objects and their dynamics. The notion of an abstract object, however, encompasses a w…
Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks
Róbert Csordás, Sjoerd van Steenkiste, Jürgen Schmidhuber
Neural networks (NNs) whose subnetworks implement reusable functions are expected to offer numerous advantages, including compositionality through efficient recombination of functi…
Improving Generalization in Meta Reinforcement Learning using Learned Objectives
Louis Kirsch, Sjoerd van Steenkiste, Jürgen Schmidhuber
Biological evolution has distilled the experiences of many learners into the general learning algorithms of humans. Our novel meta reinforcement learning algorithm MetaGenRL is ins…