A transformer policy distilled from a privileged RL teacher enables 3.1x faster real-world cube rotation on the ORCA hand using solely joint sensor data by extracting implicit object state from temporal joint patterns.
Real-world humanoid locomotion with reinforcement learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.RO 2years
2026 2representative citing papers
Abstract simulators can be grounded to real tasks by making their dynamics history-dependent and correcting them with real data, enabling RL policy transfer.
citing papers explorer
-
Learning Robust Dexterous In-Hand Manipulation from Joint Sensors with Proprioceptive Transformer
A transformer policy distilled from a privileged RL teacher enables 3.1x faster real-world cube rotation on the ORCA hand using solely joint sensor data by extracting implicit object state from temporal joint patterns.
-
Abstract Sim2Real through Approximate Information States
Abstract simulators can be grounded to real tasks by making their dynamics history-dependent and correcting them with real data, enabling RL policy transfer.