@article{parallelqlearningscalingoffpolicy,
  title = {Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation},
  author = {Zechu Li and Tao Chen and Zhang-Wei Hong and Anurag Ajay and Pulkit Agrawal},
  year = {2023},
  eprint = {2307.12983},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2307.12983v1},
}