@article{onpolicypolicygradientreinforcement,
  title = {On-Policy Policy Gradient Reinforcement Learning Without On-Policy Sampling},
  author = {Nicholas E. Corrado and Josiah P. Hanna},
  year = {2023},
  eprint = {2311.08290},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.08290v2},
}