@article{efficienttwophaseofflinedeep,
  title = {Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions},
  author = {Yinglun Xu and Tarun Suresh and Rohan Gumaste and David Zhu and Ruirui Li and Zhengyang Wang and Haoming Jiang and Xianfeng Tang and Qingyu Yin and Monica Xiao Cheng and Qi Zeng and Chao Zhang and Gagandeep Singh},
  year = {2023},
  eprint = {2401.00330},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.00330v3},
}