% Key papers for Adversarial MDPs with bandit feedback (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2019_online_37617,
  title = {{Online Convex Optimization in Adversarial Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3679},
}

@inproceedings{icml2020_learning_38367,
  title = {{Learning Adversarial Markov Decision Processes with Bandit Feedback and Unknown Transition}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5892},
}

@inproceedings{neurips2019_online_58756,
  title = {{Online Stochastic Shortest Path with Bandit Feedback and Unknown Transition Function}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13420},
}

@inproceedings{neurips2020_simultaneously_60835,
  title = {{Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17260},
}

@inproceedings{neurips2020_upper_61064,
  title = {{Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18460},
}

@inproceedings{aaai2022_learning_2312,
  title = {{Learning Adversarial Markov Decision Processes with Delayed Feedback}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/07281-learning-adversarial-markov-decision-processes-with-delayed-feedback/},
}

@inproceedings{neurips2022_follow_63773,
  title = {{Follow-the-Perturbed-Leader for Adversarial Markov Decision Processes with Bandit Feedback}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54395},
}

@inproceedings{neurips2022_improved_65062,
  title = {{Improved Regret Analysis for Variance-Adaptive Linear Bandits and Horizon-Free Linear Mixture MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54191},
}

@inproceedings{neurips2022_near_65095,
  title = {{Near-Optimal Regret for Adversarial MDP with Delayed Bandit Feedback}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54100},
}

@inproceedings{neurips2023_no_66559,
  title = {{No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73055},
}

@inproceedings{aaai2025_logarithmic_9812,
  title = {{Logarithmic Regret for Linear Markov Decision Processes with Adversarial Corruptions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34436},
}

@inproceedings{iclr2024_towards_33698,
  title = {{Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19377},
}

@inproceedings{icml2022_cooperative_40383,
  title = {{Cooperative Online Learning in Stochastic and Adversarial MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16099},
}

@inproceedings{icml2022_dynamic_40482,
  title = {{Dynamic Regret of Online Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17645},
}

@inproceedings{icml2025_near_46703,
  title = {{Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45869},
}

@inproceedings{icml2025_an_48073,
  title = {{An Optimistic Algorithm for online CMDPS with Anytime Adversarial Constraints}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44534},
}

@inproceedings{icml2025_learning_48767,
  title = {{Learning Adversarial MDPs with Stochastic Hard Constraints}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43855},
}

@inproceedings{icml2026_data_50473,
  title = {{Data- and Variance-dependent Regret Bounds for Online Tabular MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=CeDYwcRJOC},
}

@inproceedings{icml2026_best_53830,
  title = {{Best-of-Both-Worlds for Heavy-Tailed Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=j6gXeiPJ3z},
}

@inproceedings{neurips2021_the_61161,
  title = {{The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26352},
}

@inproceedings{neurips2024_beating_70602,
  title = {{Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96516},
}

@inproceedings{neurips2025_adapting_75792,
  title = {{Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=C3sKfe8e1n},
}

@inproceedings{iclr2026_learning_86748,
  title = {{Learning in Prophet Inequalities with Noisy Observations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=TOyf8Z4y22},
}

@inproceedings{icml2024_online_44385,
  title = {{Online Learning in CMDPs: Handling Stochastic and Adversarial Constraints}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34067},
}

@inproceedings{iclr2026_minimax_86467,
  title = {{Minimax Optimal Adversarial Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=QEcSLhfOoQ},
}

@inproceedings{iclr2026_primal_87438,
  title = {{Primal-Dual Policy Optimization for Adversarial Linear CMDPs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=baP3Dw7bWO},
}

@inproceedings{neurips2026_policy_92444,
  title = {{Policy Optimization in Tabular MDPs: Data-dependent Regret under Unknown Transitions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/150629},
}