Skip to content
conftrace_
2025 ICML ICML 2025

Policy-labeled Preference Learning: Is Preference Enough for RLHF?

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

❓ The Questioner

Authors

Taehyun Cho, Seokhun Ju, Seungyub Han, Dohyeong Kim, Kyungjae Lee, Jungwoo Lee

Topics

Reinforcement Learning > Methods > Offline RL Reinforcement Learning > Methods > Policy Learning Reinforcement Learning > Applications > Robotics

Keywords

direct preference optimization offline rlhf contrastive kl regularization policy-labeled preference learning regret-based modeling sequential contrastive learning
Download PDF