@article{efficientlytrainingonpolicyactorcritic,
  title = {Efficiently Training On-Policy Actor-Critic Networks in Robotic Deep Reinforcement Learning with Demonstration-like Sampled Exploration},
  author = {Zhaorun Chen and Binhao Chen and Shenghan Xie and Liang Gong and Chengliang Liu and Zhengfeng Zhang and Junping Zhang},
  year = {2021},
  eprint = {2109.13005},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2109.13005v1},
}