@article{reinforcementlearningwithhumanfeedback,
  title = {Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism},
  author = {Zihao Li and Zhuoran Yang and Mengdi Wang},
  year = {2023},
  eprint = {2305.18438},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.18438v3},
}