RAD augments reasoning-based robot policies with chain-of-thought labels from action-free human videos, improving cross-embodiment transfer and generalization on pick-and-place tasks.
Learn- ing generalizable robotic reward functions from” in-the- wild” human videos
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Action-Free Reasoning for Policy Generalization
RAD augments reasoning-based robot policies with chain-of-thought labels from action-free human videos, improving cross-embodiment transfer and generalization on pick-and-place tasks.