@article{learningrewardmachinesfrompartially,
  title = {Learning Reward Machines from Partially Observed Policies},
  author = {Mohamad Louai Shehab and Antoine Aspeel and Necmiye Ozay},
  year = {2025},
  eprint = {2502.03762},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.03762v2},
}