@article{regressingtherelativefutureefficient,
  title = {Regressing the Relative Future: Efficient Policy Optimization for Multi-turn RLHF},
  author = {Zhaolin Gao and Wenhao Zhan and Jonathan D. Chang and Gokul Swamy and Kianté Brantley and Jason D. Lee and Wen Sun},
  year = {2024},
  eprint = {2410.04612},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.04612v1},
}