@article{improperlearningwithgradientbasedpolicy,
  title = {Improper Reinforcement Learning with Gradient-based Policy Optimization},
  author = {Mohammadi Zaki and Avinash Mohan and Aditya Gopalan and Shie Mannor},
  year = {2021},
  eprint = {2102.08201},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2102.08201v3},
}