AI RESEARCH
From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning
arXiv CS.LG
•
ArXi:2606.01123v1 Announce Type: new Preference-based reinforcement learning (PbRL) avoids explicit reward engineering by learning from pairwise human preference feedback. Existing offline PbRL methods typically follow a two-stage pipeline, first learning a reward or preference model from labeled preferences and then performing offline RL on unlabeled data. We revisit offline PbRL through the lens of reward-free representation learning (RFRL) from the zero-shot RL literature, and propose a new.