@article{improvedpolicyoptimizationforonline,
  title = {Improved Policy Optimization for Online Imitation Learning},
  author = {Jonathan Wilder Lavington and Sharan Vaswani and Mark Schmidt},
  year = {2022},
  eprint = {2208.00088},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2208.00088v1},
}