@article{learninginmarkovianbanditswithnonobserva,
  title = {Learning in Markovian bandits with non-observable states and constrained decision epochs},
  author = {Thomas Hira and Victor Boone and Urtzi Ayesta and Ina Maria Verloop},
  year = {2026},
  eprint = {2606.27448},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.27448},
}