@article{pairwiseproximalpolicyoptimization,
  title = {Pairwise Proximal Policy Optimization: Harnessing Relative Feedback for LLM Alignment},
  author = {Tianhao Wu and Banghua Zhu and Ruoyu Zhang and Zhaojin Wen and Kannan Ramchandran and Jiantao Jiao},
  year = {2023},
  eprint = {2310.00212},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2310.00212v3},
}