@article{rebelaregularizationbasedsolutionfor,
  title = {REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback},
  author = {Souradip Chakraborty and Anukriti Singh and Amisha Bhaskar and Pratap Tokekar and Dinesh Manocha and Amrit Singh Bedi},
  year = {2023},
  eprint = {2312.14436},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.14436v3},
}