@article{modificationconsideringvaluelearningforr,
  title = {Modification-Considering Value Learning for Reward Hacking Mitigation in RL},
  author = {Evgenii Opryshko and Umangi Jain and Igor Gilitschenski},
  year = {2026},
  eprint = {2606.28955},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.28955},
}