@article{asynchronousrlhffasterandmoreefficient,
  title = {Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models},
  author = {Michael Noukhovitch and Shengyi Huang and Sophie Xhonneux and Arian Hosseini and Rishabh Agarwal and Aaron Courville},
  year = {2024},
  eprint = {2410.18252},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.18252v1},
}