@article{delayadaptedpolicyoptimizationand,
  title = {Delay-Adapted Policy Optimization and Improved Regret for Adversarial MDP with Delayed Bandit Feedback},
  author = {Tal Lancewicki and Aviv Rosenberg and Dmitry Sotnikov},
  year = {2023},
  eprint = {2305.07911},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.07911v1},
}