@article{continuoustimereinforcementlearningellip,
  title = {Continuous-time reinforcement learning: ellipticity enables model-free value function approximation},
  author = {Wenlong Mou},
  year = {2026},
  eprint = {2602.06930},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.06930},
}