4 papers · 1 filter
FoMo Rewards: Can we cast foundation models as reward functions?
Ekdeep Singh Lubana, Johann Brehmer, Pim de Haan +1
We explore the viability of casting foundation models as generic reward functions for reinforcement learning. To this end, we propose a simple pipeline that interfaces an off-the-s…
Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers
Pim de Haan, Taco Cohen, Johann Brehmer
The Geometric Algebra Transformer (GATr) is a versatile architecture for geometric deep learning based on projective geometric algebra. We generalize this architecture into a bluep…
Geometric Algebra Transformer
Johann Brehmer, Pim de Haan, Sönke Behrends +1
Problems involving geometric data arise in physics, chemistry, robotics, computer vision, and many other fields. Such data can take numerous forms, for instance points, direction v…
EDGI: Equivariant Diffusion for Planning with Embodied Agents
Johann Brehmer, Joey Bose, Pim de Haan +1
Embodied agents operate in a structured world, often solving tasks with spatial, temporal, and permutation symmetries. Most algorithms for planning and model-based reinforcement le…