CLARIFY uses contrastive learning on preference data to embed trajectories, then rejection-samples queries that humans can distinguish clearly, improving offline preference-based RL.
Active preference-based gaussian process regression for reward learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries
CLARIFY uses contrastive learning on preference data to embed trajectories, then rejection-samples queries that humans can distinguish clearly, improving offline preference-based RL.