@misc{gao2022scaling,
  title={Scaling Laws for Reward Model Overoptimization},
  author={Leo Gao and John Schulman and Jacob Hilton},
  year={2022},
  eprint={2210.10760},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2210.10760}
}