@article{zerothorderpolicygradientfor,
  title = {Zeroth-Order Policy Gradient for Reinforcement Learning from Human Feedback without Reward Inference},
  author = {Qining Zhang and Lei Ying},
  year = {2024},
  eprint = {2409.17401},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2409.17401v1},
}