% Key papers for Non-stationary and structured MDPs (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2018_near_57417,
  title = {{Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11305},
}

@inproceedings{neurips2017_learning_56433,
  title = {{Learning Unknown Markov Decision Processes: A Thompson Sampling Approach}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8925},
}

@inproceedings{neurips2018_exploration_57115,
  title = {{Exploration in Structured Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11847},
}

@inproceedings{icml2020_reinforcement_38688,
  title = {{Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5829},
}

@inproceedings{icml2021_provably_39829,
  title = {{Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9889},
}

@inproceedings{aaai2021_a_44,
  title = {{A Sample-Efficient Algorithm for Episodic Finite-Horizon MDP with Constraints}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/08030-a-sample-efficient-algorithm-for-episodic-finite-horizon-mdp-with-constraints/},
}

@inproceedings{aaai2022_reinforcement_2629,
  title = {{Reinforcement Learning Augmented Asymptotically Optimal Index Policy for Finite-Horizon Restless Bandits}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/08726-reinforcement-learning-augmented-asymptotically-optimal-index-policy-for-finite-horizon-restless-bandits/},
}

@inproceedings{neurips2021_regime_61292,
  title = {{Regime Switching Bandits}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28318},
}

@inproceedings{aaai2017_fast_104595,
  title = {{Fast-Tracking Stationary MOMDPs for Adaptive Management Problems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11173},
}

@inproceedings{aaai2016_bounded_105058,
  title = {{Bounded Optimal Exploration in MDP}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10230},
}

@inproceedings{aaai2022_online_2504,
  title = {{Online Apprenticeship Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/08240-online-apprenticeship-learning/},
}

@inproceedings{icml2018_problem_36934,
  title = {{Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2433},
}

@inproceedings{neurips2021_local_61386,
  title = {{Local Differential Privacy for Regret Minimization in Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27211},
}

@inproceedings{neurips2021_policy_62452,
  title = {{Policy Optimization in Adversarial MDPs: Improved Exploration via Dilated Bonuses}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27767},
}

@inproceedings{neurips2022_computationally_64477,
  title = {{Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53599},
}

@inproceedings{aaai2024_online_6849,
  title = {{Online Markov Decision Processes Configuration with Continuous Decision Space}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29344},
}

@inproceedings{neurips2021_learning_63340,
  title = {{Learning in Non-Cooperative Configurable Markov Decision Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27517},
}

@inproceedings{aaai2025_online_10196,
  title = {{Online MDP with Prototypes Information: A Robust Adaptive Approach}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34283},
}

@inproceedings{neurips2022_learning_63838,
  title = {{Learning Infinite-Horizon Average-Reward Restless Multi-Action Bandits via Index Awareness}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55105},
}

@inproceedings{iclr2024_provably_35042,
  title = {{Provably Efficient UCB-type Algorithms For Learning Predictive State Representations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18032},
}

@inproceedings{icml2024_provably_45467,
  title = {{Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32984},
}

@inproceedings{icml2025_online_47961,
  title = {{Online Episodic Convex Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44644},
}

@inproceedings{neurips2024_warm_70226,
  title = {{Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96860},
}

@inproceedings{neurips2024_local_72076,
  title = {{Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95248},
}

@inproceedings{iclr2026_is_88288,
  title = {{Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=l8YvuTQ0FA},
}

@inproceedings{neurips2026_darling_90092,
  title = {{DARLING: Detection Augmented Reinforcement Learning with Non-Stationary Guarantees}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/151097},
}

@inproceedings{icml2025_regret_47389,
  title = {{Regret-Free Reinforcement Learning for Temporal Logic Specifications}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45203},
}