@article{rewardlearningfromsuboptimal,
  title = {Reward Learning from Suboptimal Demonstrations with Applications in Surgical Electrocautery},
  author = {Zohre Karimi and Shing-Hei Ho and Bao Thach and Alan Kuntz and Daniel S. Brown},
  year = {2024},
  eprint = {2404.07185},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2404.07185v2},
}