@article{reinforcementlearningfrombaggedrewarda,
  title = {Reinforcement Learning from Bagged Reward},
  author = {Yuting Tang and Xin-Qiang Cai and Yao-Xiang Ding and Qiyu Wu and Guoqing Liu and Masashi Sugiyama},
  year = {2024},
  eprint = {2402.03771},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.03771v3},
}