PAWS performs policy updates directly using segment-level advantage functions to align utility training with policy optimization in preference-based RL.
arXiv preprint arXiv:2409.13683 , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
PAWS: Preference Learning with Advantage-Weighted Segments
PAWS performs policy updates directly using segment-level advantage functions to align utility training with policy optimization in preference-based RL.