RL-only fine-tuning with dense geometric rewards aligns OpenVLA-OFT to a novel cable-driven robot, reaching 53.5% average success on four directional commands without any demonstration data.
SimpleVLA-RL official code repository,
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
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
RL Bootstrapping of OpenVLA-OFT for a Novel Robot Embodiment
RL-only fine-tuning with dense geometric rewards aligns OpenVLA-OFT to a novel cable-driven robot, reaching 53.5% average success on four directional commands without any demonstration data.