@misc{skalse2022defining, title={Defining and Characterizing Reward Hacking}, author={Joar Skalse and Nikolaus H. R. Howe and Dmitrii Krasheninnikov and David Krueger}, year={2022}, eprint={2209.13085}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2209.13085} }