Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data

@article{zhou2024efficient,
  title = {Efficient Online Reinforcement Learning Fine-Tuning Need Not Retain Offline Data},
  author = {Zhi-Yuan Zhou and Andy Peng and Qiyang Li and Sergey Levine and Aviral Kumar},
  year = {2024},
  journal = {International Conference on Learning Representations},
  eprint = {2412.07762},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.07762},
}