activity
20172022
most citedImproving Generalization in Meta Reinforcement Learning using Learned Objectives

59 citations · 180 across the 6 of their papers we have counts for

collaborators

12 papers

cs.LG20221 cited

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…

cs.NE202050 cited

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…

cs.CV20203 cited

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…

cs.LG2020

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…

cs.NE2020

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…

cs.LG201959 cited

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…