@article{monamyopicoptimizationwithnonmyopic,
  title = {MONA: Myopic Optimization with Non-myopic Approval Can Mitigate Multi-step Reward Hacking},
  author = {Sebastian Farquhar and Vikrant Varma and David Lindner and David Elson and Caleb Biddulph and Ian Goodfellow and Rohin Shah},
  year = {2025},
  eprint = {2501.13011},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.13011v1},
}