@article{exploitingunlabeleddataforfeedback,
  title = {Exploiting Unlabeled Data for Feedback Efficient Human Preference based Reinforcement Learning},
  author = {Mudit Verma and Siddhant Bhambri and Subbarao Kambhampati},
  year = {2023},
  eprint = {2302.08738},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2302.08738v1},
}