@article{improvingreinforcementlearningfromhuman,
  title = {Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble},
  author = {Shun Zhang and Zhenfang Chen and Sunli Chen and Yikang Shen and Zhiqing Sun and Chuang Gan},
  year = {2024},
  eprint = {2401.16635},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2401.16635v3},
}