@misc{cisnerosvelarde2022policy,
  title={One Policy is Enough: Parallel Exploration with a Single Policy is Near-Optimal for Reward-Free Reinforcement Learning},
  author={Pedro Cisneros-Velarde and Boxiang Lyu and Sanmi Koyejo and Mladen Kolar},
  year={2022},
  eprint={2205.15891},
  archivePrefix={arXiv},
  primaryClass={cs.LG},
  url={https://arxiv.org/abs/2205.15891}
}