@article{rewardlearningasdoublynonparametric1,
  title = {Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws},
  author = {Kush Bhatia and Wenshuo Guo and Jacob Steinhardt},
  year = {2023},
  eprint = {2302.12349},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2302.12349v1},
}