@misc{nabail2026ubp2,
 archiveprefix = {arXiv},
 author = {Mohamed Nabail and Leo Cheng and Jingmin Wang and Nicholas Rhinehart},
 eprint = {2606.19328},
 primaryclass = {cs.LG},
 title = {UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning},
 url = {https://arxiv.org/abs/2606.19328},
 year = {2026}
}
