@article{listwiserewardestimationforoffline,
  title = {Listwise Reward Estimation for Offline Preference-based Reinforcement Learning},
  author = {Heewoong Choi and Sangwon Jung and Hongjoon Ahn and Taesup Moon},
  year = {2024},
  eprint = {2408.04190},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.04190v1},
}