@article{polynomialregretconcentrationofucbfor,
  title = {Polynomial Regret Concentration of UCB for Non-Deterministic State Transitions},
  author = {Can Cömer and Jannis Blüml and Cedric Derstroff and Kristian Kersting},
  year = {2025},
  eprint = {2502.06900},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2502.06900v1},
}