@article{analternatepolicygradientestimatorfor,
  title = {An Alternate Policy Gradient Estimator for Softmax Policies},
  author = {Shivam Garg and Samuele Tosatto and Yangchen Pan and Martha White and A. Rupam Mahmood},
  year = {2021},
  eprint = {2112.11622},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2112.11622v2},
}