@misc{zheng2023secrets, title={Secrets of RLHF in Large Language Models Part I: PPO}, author={Rui Zheng and Shihan Dou and Songyang Gao and Wei Shen and Binghai Wang and Yan Liu and Senjie Jin and Qin Liu and Limao Xiong and Lu Chen and Zhiheng Xi and Yuhao Zhou and Nuo Xu and Wenbin Lai and Minghao Zhu and Rongxiang Weng and Wensen Cheng and Cheng Chang and Zhangyue Yin and Yuan Hua and Haoran Huang and Tianxiang Sun and Hang Yan and Tao Gui and Qi Zhang and Xipeng Qiu and Xuanjing Huang}, year={2023}, eprint={2307.04964}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2307.04964} }