% Key papers for Robust MDP policy gradient (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2016_safe_55975,
  title = {{Safe Exploration in Finite Markov Decision Processes with Gaussian Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/6946},
}

@inproceedings{aaai2018_safe_103413,
  title = {{Safe Exploration and Optimization of Constrained MDPs Using Gaussian Processes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12103},
}

@inproceedings{aaai2018_ltlf_101488,
  title = {{LTLf/LDLf Non-Markovian Rewards}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11572},
}

@inproceedings{aaai2020_reinforcement_101953,
  title = {{Reinforcement Learning with Non-Markovian Rewards}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5814},
}

@inproceedings{icml2020_safe_38724,
  title = {{Safe Reinforcement Learning in Constrained Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5904},
}

@inproceedings{aaai2016_exploiting_105162,
  title = {{Exploiting Anonymity in Approximate Linear Programming: Scaling to Large Multiagent MDPs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10133},
}

@inproceedings{icml2021_robust_39896,
  title = {{Robust Reinforcement Learning using Least Squares Policy Iteration with Provable Performance Guarantees}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8693},
}

@inproceedings{icml2020_a_37875,
  title = {{A Markov Decision Process Model for Socio-Economic Systems Impacted by Climate Change}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6436},
}

@inproceedings{neurips2019_real_58882,
  title = {{Real-Time Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13488},
}

@inproceedings{aaai2017_hindsight_103357,
  title = {{Hindsight Optimization for Hybrid State and Action MDPs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11056},
}

@inproceedings{icml2019_kernel_37463,
  title = {{Kernel-Based Reinforcement Learning in Robust Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3984},
}

@inproceedings{icml2020_understanding_38900,
  title = {{Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5901},
}

@inproceedings{neurips2018_policy_57516,
  title = {{Policy-Conditioned Uncertainty Sets for Robust Markov Decision Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11853},
}

@inproceedings{icml2020_symbolic_38825,
  title = {{Symbolic Network: Generalized Neural Policies for Relational MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5784},
}

@inproceedings{aaai2020_querying_101241,
  title = {{Querying to Find a Safe Policy under Uncertain Safety Constraints in Markov Decision Processes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5638},
}

@inproceedings{aaai2020_reinforcement_101880,
  title = {{Reinforcement Learning When All Actions Are Not Always Available}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5740},
}

@inproceedings{aaai2023_robust_4542,
  title = {{Robust Average-Reward Markov Decision Processes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26775},
}

@inproceedings{neurips2021_twice_63500,
  title = {{Twice regularized MDPs and the equivalence between robustness and regularization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27737},
}

@inproceedings{neurips2021_risk_63541,
  title = {{Risk-Averse Bayes-Adaptive Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28061},
}

@inproceedings{iclr2021_learning_30516,
  title = {{Learning Robust State Abstractions for Hidden-Parameter Block MDPs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2847},
}

@inproceedings{aaai2024_solving_7367,
  title = {{Solving Non-rectangular Reward-Robust MDPs via Frequency Regularization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30101},
}

@inproceedings{neurips2024_efficient_71679,
  title = {{Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95603},
}

@inproceedings{aaai2024_omega_6817,
  title = {{Omega-Regular Decision Processes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30105},
}

@inproceedings{aaai2024_optimizing_6877,
  title = {{Optimizing Local Satisfaction of Long-Run Average Objectives in Markov Decision Processes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29993},
}

@inproceedings{iclr2024_beyond_33490,
  title = {{Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19585},
}

@inproceedings{iclr2024_soft_34804,
  title = {{Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18270},
}

@inproceedings{icml2024_bring_44522,
  title = {{Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33930},
}

@inproceedings{icml2024_saver_45508,
  title = {{SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32944},
}

@inproceedings{neurips2024_time_71852,
  title = {{Time-Constrained Robust MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95448},
}

@inproceedings{neurips2024_rl_73551,
  title = {{RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93928},
}

@inproceedings{iclr2025_how_82162,
  title = {{How to Find the Exact Pareto Front for Multi-Objective MDPs?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29630},
}

@inproceedings{aaai2025_approximate_8134,
  title = {{Approximate Bilevel Difference Convex Programming for Bayesian Risk Markov Decision Processes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34862},
}

@inproceedings{aaai2025_risk_10566,
  title = {{Risk-averse Total-reward MDPs with ERM and EVaR}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34275},
}

@inproceedings{icml2024_a_44545,
  title = {{A Single-Loop Robust Policy Gradient Method for Robust Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33907},
}

@inproceedings{icml2025_model_46754,
  title = {{Model-Based Exploration in Monitored Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45819},
}

@inproceedings{icml2026_dynamic_54386,
  title = {{Dynamic Programming for Epistemic Uncertainty in Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=oUv02QKUxG},
}

@inproceedings{icml2026_off_55125,
  title = {{Off-Policy Evaluation for Missingness-Aware Policies in MDPs with Rewards Missing Not at Random}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=vpSFJoxyDz},
}

@inproceedings{neurips2025_efficient_75014,
  title = {{Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=3MiADMHY62},
}

@inproceedings{neurips2025_linear_76155,
  title = {{Linear Mixture Distributionally Robust Markov Decision Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=GA3NBpzQ1x},
}

@inproceedings{neurips2025_ns_77867,
  title = {{NS-Gym: A Comprehensive and Open-Source Simulation Framework for Non-Stationary Markov Decision Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=YOXZuRy40U},
}