76 citations · 201 across the 20 of their papers we have counts for
4 papers · 1 filter
Compositional Multi-Object Reinforcement Learning with Linear Relation Networks
Davide Mambelli, Frederik Träuble, Stefan Bauer +2
Although reinforcement learning has seen remarkable progress over the last years, solving robust dexterous object-manipulation tasks in multi-object settings remains a challenge. I…
Physical Derivatives: Computing policy gradients by physical forward-propagation
Arash Mehrjou, Ashkan Soleymani, Stefan Bauer +1
Model-free and model-based reinforcement learning are two ends of a spectrum. Learning a good policy without a dynamic model can be prohibitively expensive. Learning the dynamic mo…
CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
Ossama Ahmed, Frederik Träuble, Anirudh Goyal +5
Despite recent successes of reinforcement learning (RL), it remains a challenge for agents to transfer learned skills to related environments. To facilitate research addressing thi…
TriFinger: An Open-Source Robot for Learning Dexterity
Manuel Wüthrich, Felix Widmaier, Felix Grimminger +12
Dexterous object manipulation remains an open problem in robotics, despite the rapid progress in machine learning during the past decade. We argue that a hindrance is the high cost…