118 citations · 345 across the 24 of their papers we have counts for
8 papers · 1 filter
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…
Unsupervised Learning of Temporal Abstractions with Slot-based Transformers
Anand Gopalakrishnan, Kazuki Irie, Jürgen Schmidhuber +1
The discovery of reusable sub-routines simplifies decision-making and planning in complex reinforcement learning problems. Previous approaches propose to learn such temporal abstra…
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…
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…