@article{marlhfreinforcementlearningfromhuman,
  title = {MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions},
  author = {Yekun Chai and Haoran Sun and Huang Fang and Shuohuan Wang and Yu Sun and Hua Wu},
  year = {2024},
  eprint = {2410.02743},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.02743v1},
}