UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based RL

arXiv·medium signal

Proposes selecting which behavior pairs to query for human preferences based on uncertainty balancing, making preference-based RL more sample-efficient by reducing the number of comparisons needed to learn a reward model. Relevant to anyone building RLHF/preference pipelines where human labeling is the cost bottleneck. By Mohamed Nabail, Leo Cheng, Jingmin Wang et al. (cs.LG/cs.AI/cs.RO).