@article{greensimulationassistedpolicygradientto,
  title = {Variance Reduction based Experience Replay for Policy Optimization},
  author = {Hua Zheng and Wei Xie and M. Ben Feng},
  year = {2021},
  eprint = {2110.08902},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2110.08902v4},
}