@article{bestofbothworldspolicyoptimizationfor,
  title = {Best-of-Both-Worlds Policy Optimization for CMDPs with Bandit Feedback},
  author = {Francesco Emanuele Stradi and Anna Lunghi and Matteo Castiglioni and Alberto Marchesi and Nicola Gatti},
  year = {2024},
  eprint = {2410.02269},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.02269v1},
}