570 citations · 3k across the 41 of their papers we have counts for
48 papers
BISCUIT: Causal Representation Learning from Binary Interactions
Phillip Lippe, Sara Magliacane, Sindy Löwe +3
Identifying the causal variables of an environment and how to intervene on them is of core value in applications such as robotics and embodied AI. While an agent can commonly inter…
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…
Deconfounding Imitation Learning with Variational Inference
Risto Vuorio, Pim de Haan, Johann Brehmer +3
Standard imitation learning can fail when the expert demonstrators have different sensory inputs than the imitating agent. This is because partial observability gives rise to hidde…
A PAC-Bayesian Generalization Bound for Equivariant Networks
Arash Behboodi, Gabriele Cesa, Taco Cohen
Equivariant networks capture the inductive bias about the symmetry of the learning task by building those symmetries into the model. In this paper, we study how equivariance relate…
Towards a Grounded Theory of Causation for Embodied AI
Taco Cohen
There exist well-developed frameworks for causal modelling, but these require rather a lot of human domain expertise to define causal variables and perform interventions. In order…