@article{sampleefficienthypergradientestimationfo,
  title = {Sample-Efficient Hypergradient Estimation for Decentralized Bi-Level Reinforcement Learning},
  author = {Mikoto Kudo and Takumi Tanabe and Akifumi Wachi and Youhei Akimoto},
  year = {2026},
  eprint = {2603.14867},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.14867},
}