@inproceedings{learningadversarialmarkovdecision,
  title = {Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition},
  author = {Chi Jin and Tiancheng Jin and Haipeng Luo and Suvrit Sra and Tiancheng Yu},
  year = {2020},
  booktitle = {ICML 2020 1},
  url = {https://proceedings.icml.cc/static/paper_files/icml/2020/879-Paper.pdf},
}