% Key papers for POMDPs and confounded RL (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2020_mitigating_15893,
  title = {{Mitigating Bias in Face Recognition Using Skewness-Aware Reinforcement Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2018_a_56800,
  title = {{A Lyapunov-based Approach to Safe Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11775},
}

@inproceedings{aaai2019_classification_101592,
  title = {{Classification with Costly Features Using Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4287},
}

@inproceedings{aaai2020_uncertainty_102174,
  title = {{Uncertainty-Aware Action Advising for Deep Reinforcement Learning Agents}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6036},
}

@inproceedings{icml2019_counterfactual_37256,
  title = {{Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4272},
}

@inproceedings{aaai2019_generation_101224,
  title = {{Generation of Policy-Level Explanations for Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4097},
}

@inproceedings{aaai2019_deep_103220,
  title = {{Deep Reactive Policies for Planning in Stochastic Nonlinear Domains}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4744},
}

@inproceedings{aaai2021_iterative_816,
  title = {{Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methods}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/09923-iterative-bounding-mdps-learning-interpretable-policies-via-non-interpretable-methods/},
}

@inproceedings{neurips2018_dual_57073,
  title = {{Dual Policy Iteration}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11680},
}

@inproceedings{neurips2020_on_60462,
  title = {{On Efficiency in Hierarchical Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17932},
}

@inproceedings{icml2017_unifying_36444,
  title = {{Unifying Task Specification in Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/461},
}

@inproceedings{aaai2020_lifelong_101879,
  title = {{Lifelong Learning with a Changing Action Set}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5739},
}

@inproceedings{iclr2020_observational_29472,
  title = {{Observational Overfitting in Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=HJli2hNKDH},
}

@inproceedings{icml2020_constrained_38040,
  title = {{Constrained Markov Decision Processes via Backward Value Functions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6226},
}

@inproceedings{neurips2020_inverse_60108,
  title = {{Inverse Rational Control with Partially Observable Continuous Nonlinear Dynamics}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17305},
}

@inproceedings{aaai2021_metrics_989,
  title = {{Metrics and Continuity in Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/08261-metrics-and-continuity-in-reinforcement-learning/},
}

@inproceedings{aaai2019_vidyutvanika_100172,
  title = {{VidyutVanika: A Reinforcement Learning Based Broker Agent for a Power Trading Competition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/3880},
}

@inproceedings{aaai2021_exact_552,
  title = {{Exact Reduction of Huge Action Spaces in General Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/08874-exact-reduction-of-huge-action-spaces-in-general-reinforcement-learning/},
}

@inproceedings{iclr2021_vulnerability_30072,
  title = {{Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2665},
}

@inproceedings{neurips2020_adaptive_59321,
  title = {{Adaptive Experimental Design with Temporal Interference: A Maximum Likelihood Approach}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17926},
}

@inproceedings{aaai2025_probabilistic_10365,
  title = {{Probabilistic Shielding for Safe Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33767},
}

@inproceedings{aaai2024_long_6548,
  title = {{Long-Term Safe Reinforcement Learning with Binary Feedback}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30164},
}

@inproceedings{aaai2025_real_10474,
  title = {{Real-Time Recurrent Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34001},
}

@inproceedings{neurips2024_provable_73863,
  title = {{Provable Partially Observable Reinforcement Learning with Privileged Information}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93646},
}

@inproceedings{aaai2024_personalized_6948,
  title = {{Personalized Reinforcement Learning with a Budget of Policies}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29169},
}

@inproceedings{neurips2024_flipping_70709,
  title = {{Flipping-based Policy for Chance-Constrained Markov Decision Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96415},
}

@inproceedings{aaai2025_grsn_9292,
  title = {{GRSN: Gated Recurrent Spiking Neurons for POMDPs and MARL}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32139},
}

@inproceedings{iclr2024_goodhart_33662,
  title = {{Goodhart's Law in Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19413},
}

@inproceedings{iclr2024_bridging_35194,
  title = {{Bridging State and History Representations: Understanding Self-Predictive RL}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17879},
}

@inproceedings{neurips2024_taming_71077,
  title = {{Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96136},
}

@inproceedings{neurips2024_on_72109,
  title = {{On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95220},
}

@inproceedings{neurips2024_recurrent_73795,
  title = {{Recurrent Reinforcement Learning with Memoroids}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93712},
}

@inproceedings{iclr2024_submodular_35155,
  title = {{Submodular Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17918},
}

@inproceedings{icml2024_geometric_43340,
  title = {{Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35112},
}

@inproceedings{icml2024_predictive_44004,
  title = {{Predictive Performance Comparison of Decision Policies Under Confounding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34448},
}

@inproceedings{icml2024_rl_45395,
  title = {{RL-CFR: Improving Action Abstraction for Imperfect Information Extensive-Form Games with Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33056},
}

@inproceedings{icml2025_reinforcement_45911,
  title = {{Reinforcement Learning with Segment Feedback}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46633},
}

@inproceedings{icml2025_learning_46534,
  title = {{Learning Utilities from Demonstrations in Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46034},
}

@inproceedings{icml2025_intersectional_47889,
  title = {{Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44714},
}

@inproceedings{icml2025_partially_47902,
  title = {{Partially Observable Reinforcement Learning with Memory Traces}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44701},
}