ARM trains reward models on Progressive/Regressive/Stagnant labels to enable adaptive reweighting in offline RL, reaching 99.4% success on towel-folding with minimal human intervention.
Deep reinforcement learn- ing from human preferences
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
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
ARM: Advantage Reward Modeling for Long-Horizon Manipulation
ARM trains reward models on Progressive/Regressive/Stagnant labels to enable adaptive reweighting in offline RL, reaching 99.4% success on towel-folding with minimal human intervention.