@article{gapdependentboundsforqlearningusing,
  title = {Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition},
  author = {Zhong Zheng and Haochen Zhang and Lingzhou Xue},
  year = {2024},
  eprint = {2410.07574},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.07574v1},
}