@article{ubp2uncertaintybalancedpreferenceplannin, title = {UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning}, author = {Mohamed Nabail and Leo Kaixuan Cheng and Jingmin Wang and Nicholas Rhinehart}, year = {2026}, eprint = {2606.19328}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2606.19328}, }