@article{federatedqlearningwithreferenceadvantage,
  title = {Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost},
  author = {Zhong Zheng and Haochen Zhang and Lingzhou Xue},
  year = {2024},
  eprint = {2405.18795},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2405.18795v1},
}