@article{unio4unifyingonlineandofflinedeep,
  title = {Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization},
  author = {Kun Lei and Zhengmao He and Chenhao Lu and Kaizhe Hu and Yang Gao and Huazhe Xu},
  year = {2023},
  eprint = {2311.03351},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.03351v4},
}