@article{permutationinvariantpolicyoptimizationfo,
  title = {Permutation Invariant Policy Optimization for Mean-Field Multi-Agent Reinforcement Learning: A Principled Approach},
  author = {Yan Li and Lingxiao Wang and Jiachen Yang and Ethan Wang and Zhaoran Wang and Tuo Zhao and Hongyuan Zha},
  year = {2021},
  eprint = {2105.08268},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2105.08268v1},
}