The History and Risks of Reinforcement Learning and Human Feedback

@misc{lambert2023historyrisksreinforcement,
      title={The History and Risks of Reinforcement Learning and Human Feedback}, 
      author={Nathan Lambert and Thomas Krendl Gilbert and Tom Zick},
      year={2023},
      eprint={2310.13595},
      archivePrefix={arXiv},
      primaryClass={cs.CY},
      url={https://arxiv.org/abs/2310.13595}, 
}