@inproceedings{sampleefficientreinforcementlearningfor,
  title = {Sample-Efficient Reinforcement Learning for Linearly-Parameterized MDPs with a Generative Model},
  author = {Bingyan Wang and Yuling Yan and Jianqing Fan},
  year = {2021},
  booktitle = {NeurIPS 2021 12},
  eprint = {2105.14016},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2105.14016v3},
}