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

@inproceedings{icml2020_model_38463,
  title = {{Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6520},
}

@inproceedings{neurips2019_exploration_58241,
  title = {{Exploration Bonus for Regret Minimization in Discrete and Continuous Average Reward MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13635},
}

@inproceedings{neurips2021_learning_62073,
  title = {{Learning Policies with Zero or Bounded Constraint Violation for Constrained MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26894},
}

@inproceedings{aaai2021_minimax_993,
  title = {{Minimax Regret Optimisation for Robust Planning in Uncertain Markov Decision Processes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/11930-minimax-regret-optimisation-for-robust-planning-in-uncertain-markov-decision-processes/},
}

@inproceedings{neurips2017_regret_56619,
  title = {{Regret Minimization in MDPs with Options without Prior Knowledge}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9101},
}

@inproceedings{icml2021_adaptive_39028,
  title = {{Adaptive Sampling for Best Policy Identification in Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9627},
}

@inproceedings{neurips2021_nearly_61536,
  title = {{Nearly Minimax Optimal Reinforcement Learning for Discounted MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26767},
}

@inproceedings{icml2020_tightening_38863,
  title = {{Tightening Exploration in Upper Confidence Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6471},
}

@inproceedings{neurips2019_regret_58898,
  title = {{Regret Minimization for Reinforcement Learning with Vectorial Feedback and Complex Objectives}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13304},
}

@inproceedings{neurips2020_towards_60990,
  title = {{Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18351},
}

@inproceedings{neurips2021_rl_61630,
  title = {{RL for Latent MDPs: Regret Guarantees and a Lower Bound}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28595},
}

@inproceedings{neurips2019_large_58458,
  title = {{Large Scale Markov Decision Processes with Changing Rewards}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13429},
}

@inproceedings{neurips2020_reinforcement_60691,
  title = {{Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17165},
}

@inproceedings{icml2023_regret_42903,
  title = {{Regret Bounds for Markov Decision Processes with Recursive Optimized Certainty Equivalents}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24766},
}

@inproceedings{neurips2020_stateful_60864,
  title = {{Stateful Posted Pricing with Vanishing Regret via Dynamic Deterministic Markov Decision Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18946},
}

@inproceedings{neurips2021_oracle_61602,
  title = {{Oracle-Efficient Regret Minimization in Factored MDPs with Unknown Structure}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28319},
}

@inproceedings{icml2018_efficient_36660,
  title = {{Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2036},
}

@inproceedings{icml2022_learning_40757,
  title = {{Learning Infinite-horizon Average-reward Markov Decision Process with Constraints}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17667},
}

@inproceedings{aaai2024_regret_7093,
  title = {{Regret Analysis of Policy Gradient Algorithm for Infinite Horizon Average Reward Markov Decision Processes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28973},
}

@inproceedings{icml2021_towards_40049,
  title = {{Towards Tight Bounds on the Sample Complexity of Average-reward MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9781},
}

@inproceedings{neurips2024_achieving_72235,
  title = {{Achieving Tractable Minimax Optimal Regret in Average Reward MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95107},
}

@inproceedings{neurips2024_achieving_73994,
  title = {{Achieving \$tildeO(1/epsilon)\$ Sample Complexity for Constrained Markov Decision Process}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93523},
}

@inproceedings{icml2024_no_43945,
  title = {{No-Regret Reinforcement Learning in Smooth MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34507},
}

@inproceedings{icml2025_quantum_46440,
  title = {{Quantum Speedups in Regret Analysis of Infinite Horizon Average-Reward Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46126},
}

@inproceedings{neurips2024_span_73942,
  title = {{Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93570},
}

@inproceedings{aaai2025_efficient_8917,
  title = {{Efficient Reinforcement Learning in Probabilistic Reward Machines}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34061},
}

@inproceedings{iclr2024_horizon_34477,
  title = {{Horizon-Free Regret for Linear Markov Decision Processes}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18597},
}

@inproceedings{iclr2024_sample_34904,
  title = {{Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18170},
}

@inproceedings{icml2024_test_44154,
  title = {{Test-Time Regret Minimization in Meta Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34298},
}

@inproceedings{icml2024_rate_44535,
  title = {{Rate-Optimal Policy Optimization for Linear Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33917},
}

@inproceedings{icml2024_truly_45076,
  title = {{Truly No-Regret Learning in Constrained MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33376},
}

@inproceedings{icml2024_efficient_45343,
  title = {{Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33108},
}

@inproceedings{icml2025_gap_45875,
  title = {{Gap-Dependent Bounds for Federated \$Q\$-Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46668},
}

@inproceedings{icml2026_minimax_53412,
  title = {{Minimax Optimal Strategy for Delayed Observations in Online Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=fFupHW7Jqx},
}

@inproceedings{neurips2024_achieving_70122,
  title = {{Achieving Constant Regret in Linear Markov Decision Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96956},
}

@inproceedings{neurips2025_no_74827,
  title = {{No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=1bb974Q4jJ},
}

@inproceedings{neurips2025_reinforce_77910,
  title = {{REINFORCE Converges to Optimal Policies with Any Learning Rate}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=YzriuQGaNX},
}

@inproceedings{iclr2025_optimal_82456,
  title = {{Optimal Non-Asymptotic Rates of Value Iteration for Average-Reward Markov Decision Processes}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29337},
}

@inproceedings{neurips2026_learning_92435,
  title = {{Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/151237},
}