@article{advantageawarepolicyoptimizationfor,
  title = {A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective},
  author = {Yunpeng Qing and Shunyu Liu and Jingyuan Cong and KaiXuan Chen and Yihe Zhou and Mingli Song},
  year = {2024},
  eprint = {2403.07262},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.07262v4},
}