@article{nearlyoptimalregretforlearning,
  title = {Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs},
  author = {Jiafan He and Dongruo Zhou and Quanquan Gu},
  year = {2021},
  eprint = {2102.08940},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2102.08940v2},
}