arXiv · 2025 · Preprint

RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization

Zeng Zhiyuan, Jiashuo Liu, Zhangyue Yin, Ge Zhang, Wenhao Huang, Xipeng Qiu

Date
2025-11-06
Citations
1
arXiv
2511.04285
Cite
@misc{zhiyuan2025rloop,
  title = {RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initialization},
  author = {Zeng Zhiyuan and Jiashuo Liu and Zhangyue Yin and Ge Zhang and Wenhao Huang and Xipeng Qiu},
  year = {2025},
  eprint = {2511.04285},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.04285},
}