4 papers · 1 filter
Relative Value Learning
Marc Höftmann, Jan Robine, Stefan Harmeling
In reinforcement learning, critics typically estimate absolute state values , estimating how good a particular situation is in isolation. However, it turns out that only diff…
Simple, Good, Fast: Self-Supervised World Models Free of Baggage
Jan Robine, Marc Höftmann, Stefan Harmeling
What are the essential components of world models? How far do we get with world models that are not employing RNNs, transformers, discrete representations, and image reconstruction…
Just Cluster It: An Approach for Exploration in High-Dimensions using Clustering and Pre-Trained Representations
Stefan Sylvius Wagner, Stefan Harmeling
In this paper we adopt a representation-centric perspective on exploration in reinforcement learning, viewing exploration fundamentally as a density estimation problem. We investig…
Backward Learning for Goal-Conditioned Policies
Marc Höftmann, Jan Robine, Stefan Harmeling
Can we learn policies in reinforcement learning without rewards? Can we learn a policy just by trying to reach a goal state? We answer these questions positively by proposing a mul…