% Key papers for Offline RL sample complexity theory (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2020_an_37939,
  title = {{An Optimistic Perspective on Offline Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6643},
}

@inproceedings{iclr2020_keep_29814,
  title = {{Keep Doing What Worked: Behavior Modelling Priors for Offline Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rke7geHtwH},
}

@inproceedings{icml2021_uncertainty_40071,
  title = {{Uncertainty Weighted Actor-Critic for Offline Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8869},
}

@inproceedings{iclr2020_gendice_29535,
  title = {{GenDICE: Generalized Offline Estimation of Stationary Values}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=HkxlcnVFwB},
}

@inproceedings{aaai2018_an_102451,
  title = {{An Optimal Online Method of Selecting Source Policies for Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11718},
}

@inproceedings{neurips2021_online_61812,
  title = {{Online and Offline Reinforcement Learning by Planning with a Learned Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28844},
}

@inproceedings{aaai2023_towards_4855,
  title = {{Towards Safe Mechanical Ventilation Treatment Using Deep Offline Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26862},
}

@inproceedings{neurips2021_offline_61969,
  title = {{Offline RL Without Off-Policy Evaluation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27968},
}

@inproceedings{neurips2021_bellman_62763,
  title = {{Bellman-consistent Pessimism for Offline Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27879},
}

@inproceedings{neurips2021_provable_61713,
  title = {{Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28066},
}

@inproceedings{neurips2022_a_64289,
  title = {{A Policy-Guided Imitation Approach for Offline Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55275},
}

@inproceedings{neurips2022_exploit_65723,
  title = {{Exploit Reward Shifting in Value-Based Deep-RL: Optimistic Curiosity-Based Exploration and Conservative Exploitation via Linear Reward Shaping}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55336},
}

@inproceedings{aaai2022_text_2821,
  title = {{Text-Based Interactive Recommendation via Offline Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/11694-text-based-interactive-recommendation-via-offline-reinforcement-learning/},
}

@inproceedings{iclr2021_focal_30050,
  title = {{FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3343},
}

@inproceedings{iclr2021_representation_30302,
  title = {{Representation Balancing Offline Model-based Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2653},
}

@inproceedings{iclr2022_dara_30944,
  title = {{DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/5934},
}

@inproceedings{icml2021_optidice_39741,
  title = {{OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/10187},
}

@inproceedings{icml2022_adversarially_40235,
  title = {{Adversarially Trained Actor Critic for Offline Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17173},
}

@inproceedings{iclr2022_pessimistic_31774,
  title = {{Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/7210},
}

@inproceedings{iclr2022_revisiting_31873,
  title = {{Revisiting Design Choices in Offline Model Based Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6699},
}

@inproceedings{neurips2024_diffusion_71186,
  title = {{Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96045},
}

@inproceedings{aaai2024_cudc_5363,
  title = {{CUDC: A Curiosity-Driven Unsupervised Data Collection Method with Adaptive Temporal Distances for Offline Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29437},
}

@inproceedings{neurips2024_adaptive_70340,
  title = {{Adaptive \$Q\$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96757},
}

@inproceedings{iclr2024_delphic_35145,
  title = {{Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17928},
}

@inproceedings{neurips2024_networkgym_70326,
  title = {{NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97863},
}

@inproceedings{neurips2024_a2po_73397,
  title = {{A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94058},
}

@inproceedings{icml2024_simple_45157,
  title = {{Simple Ingredients for Offline Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33295},
}

@inproceedings{icml2024_diffstitch_45419,
  title = {{DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33032},
}

@inproceedings{neurips2024_rethinking_73375,
  title = {{Rethinking Optimal Transport in Offline Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94076},
}

@inproceedings{neurips2024_constrained_73940,
  title = {{Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93572},
}

@inproceedings{iclr2025_any_81679,
  title = {{Any-step Dynamics Model Improves Future Predictions for Online and Offline Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30099},
}

@inproceedings{iclr2025_behavioral_81810,
  title = {{Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29971},
}

@inproceedings{iclr2025_on_82330,
  title = {{On Rollouts in Model-Based Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29461},
}

@inproceedings{iclr2025_learning_83862,
  title = {{Learning on One Mode: Addressing Multi-modality in Offline Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/27958},
}

@inproceedings{aaai2024_exact_5889,
  title = {{Exact Policy Recovery in Offline RL with Both Heavy-Tailed Rewards and Data Corruption}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29022},
}

@inproceedings{aaai2024_exploiting_5902,
  title = {{Exploiting Action Impact Regularity and Exogenous State Variables for Offline Reinforcement Learning (Abstract Reprint)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30606},
}

@inproceedings{iclr2024_learning_33615,
  title = {{Learning from Sparse Offline Datasets via Conservative Density Estimation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19460},
}

@inproceedings{iclr2024_reward_34044,
  title = {{Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19031},
}

@inproceedings{iclr2024_odice_34204,
  title = {{ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18871},
}

@inproceedings{icml2025_provable_45927,
  title = {{Provable Zero-Shot Generalization in Offline Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46618},
}