@article{modelfreepolicylearningwithreward,
  title = {Model-free Policy Learning with Reward Gradients},
  author = {Qingfeng Lan and Samuele Tosatto and Homayoon Farrahi and A. Rupam Mahmood},
  year = {2021},
  eprint = {2103.05147},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2103.05147v4},
}