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

@inproceedings{aaai2022_constraints_1868,
  title = {{Constraints Penalized Q-learning for Safe Offline Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/08753-constraints-penalized-q-learning-for-safe-offline-reinforcement-learning/},
}

@inproceedings{neurips2021_combo_62742,
  title = {{COMBO: Conservative Offline Model-Based Policy Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/30476},
}

@inproceedings{neurips2021_uncertainty_62537,
  title = {{Uncertainty-Based Offline Reinforcement Learning with Diversified Q-Ensemble}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/25921},
}

@inproceedings{iclr2021_what_29974,
  title = {{What are the Statistical Limits of Offline RL with Linear Function Approximation?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2830},
}

@inproceedings{neurips2022_mildly_65111,
  title = {{Mildly Conservative Q-Learning for Offline Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54993},
}

@inproceedings{iclr2022_pessimistic_31391,
  title = {{Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6030},
}

@inproceedings{icml2021_is_39482,
  title = {{Is Pessimism Provably Efficient for Offline RL?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/10409},
}

@inproceedings{neurips2021_conservative_62513,
  title = {{Conservative Offline Distributional Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27353},
}

@inproceedings{neurips2022_robust_64190,
  title = {{Robust Reinforcement Learning using Offline Data}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53040},
}

@inproceedings{neurips2022_why_66487,
  title = {{Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53737},
}

@inproceedings{aaai2024_offline_6815,
  title = {{Offline Model-Based Optimization via Policy-Guided Gradient Search}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29001},
}

@inproceedings{neurips2022_model_65977,
  title = {{Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54842},
}

@inproceedings{aaai2025_sumo_10650,
  title = {{SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34206},
}

@inproceedings{iclr2023_when_33098,
  title = {{When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11288},
}

@inproceedings{icml2022_offline_40913,
  title = {{Offline RL Policies Should Be Trained to be Adaptive}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/18003},
}

@inproceedings{aaai2024_optimistic_6871,
  title = {{Optimistic Model Rollouts for Pessimistic Offline Policy Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29607},
}

@inproceedings{iclr2023_confidence_32775,
  title = {{Confidence-Conditioned Value Functions for Offline Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10887},
}

@inproceedings{neurips2022_uncertainty_66027,
  title = {{Uncertainty Estimation Using Riemannian Model Dynamics for Offline Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54511},
}

@inproceedings{neurips2024_q_71848,
  title = {{Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95452},
}

@inproceedings{neurips2024_uncertainty_74098,
  title = {{Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93435},
}

@inproceedings{aaai2024_relaxed_7105,
  title = {{Relaxed Stationary Distribution Correction Estimation for Improved Offline Policy Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29218},
}

@inproceedings{aaai2024_neural_6765,
  title = {{Neural Network Approximation for Pessimistic Offline Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29517},
}

@inproceedings{iclr2024_improving_34238,
  title = {{Improving Offline RL by Blending Heuristics}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18837},
}

@inproceedings{neurips2024_exclusively_70282,
  title = {{Exclusively Penalized Q-learning for Offline Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96808},
}

@inproceedings{neurips2025_offline_75119,
  title = {{Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=4P6Mployhf},
}

@inproceedings{iclr2025_model_81943,
  title = {{Model-based Offline Reinforcement Learning with Lower Expectile Q-Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29841},
}

@inproceedings{aaai2025_dynamic_8854,
  title = {{Dynamic Uncertainty Estimation for Offline Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35410},
}

@inproceedings{aaai2025_selective_10713,
  title = {{Selective Uncertainty Propagation in Offline RL}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33977},
}

@inproceedings{cvpr2024_poce_24415,
  title = {{POCE: Primal Policy Optimization with Conservative Estimation for Multi-constraint Offline Reinforcement Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/29821},
}

@inproceedings{iclr2024_pessimistic_33626,
  title = {{Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19449},
}

@inproceedings{icml2024_pessimism_44035,
  title = {{Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34417},
}

@inproceedings{icml2025_stable_47342,
  title = {{Stable Offline Value Function Learning with Bisimulation-based Representations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45250},
}

@inproceedings{icml2026_vipo_52555,
  title = {{VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=XAZdspeB5d},
}

@inproceedings{icml2026_regularized_55052,
  title = {{Regularized Offline Policy Optimization with Posterior Hybrid Bayesian Belief}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=v8BF1g3u8r},
}

@inproceedings{neurips2024_deterministic_71924,
  title = {{Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95381},
}