@article{optimalityandapproximationwithpolicy,
  title = {On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift},
  author = {Alekh Agarwal and Sham M. Kakade and Jason D. Lee and Gaurav Mahajan},
  year = {2019},
  eprint = {1908.00261},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1908.00261v5},
}