@article{provablysafereinforcementlearningforstoc,
  title = {Provably Safe Reinforcement Learning for Stochastic Reach-Avoid Problems with Entropy Regularization},
  author = {Abhijit Mazumdar and Rafal Wisniewski and Manuela L. Bujorianu},
  year = {2026},
  eprint = {2601.08646},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2601.08646},
}