190 citations · 823 across the 29 of their papers we have counts for
3 papers · 1 filter
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…
A Perspective on Objects and Systematic Generalization in Model-Based RL
Sjoerd van Steenkiste, Klaus Greff, Jürgen Schmidhuber
In order to meet the diverse challenges in solving many real-world problems, an intelligent agent has to be able to dynamically construct a model of its environment. Objects facili…
Are Disentangled Representations Helpful for Abstract Visual Reasoning?
Sjoerd van Steenkiste, Francesco Locatello, Jürgen Schmidhuber +1
A disentangled representation encodes information about the salient factors of variation in the data independently. Although it is often argued that this representational format is…