% Key papers for Diffusion models for offline decision making (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2020_reinforcement_100289,
  title = {{Reinforcement-Learning Based Portfolio Management with Augmented Asset Movement Prediction States}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5462},
}

@inproceedings{aaai2021_a_18,
  title = {{A General Offline Reinforcement Learning Framework for Interactive Recommendation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/04512-a-general-offline-reinforcement-learning-framework-for-interactive-recommendation/},
}

@inproceedings{aaai2020_rl_100240,
  title = {{RL-Duet: Online Music Accompaniment Generation Using Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5413},
}

@inproceedings{icml2021_actionable_39016,
  title = {{Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9743},
}

@inproceedings{aaai2018_optimizing_101246,
  title = {{Optimizing Interventions via Offline Policy Evaluation: Studies in Citizen Science}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11489},
}

@inproceedings{icml2020_distributionally_38117,
  title = {{Distributionally Robust Policy Evaluation and Learning in Offline Contextual Bandits}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6197},
}

@inproceedings{neurips2021_provably_63363,
  title = {{Provably Efficient Causal Reinforcement Learning with Confounded Observational Data}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28819},
}

@inproceedings{icml2022_robust_41118,
  title = {{Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16239},
}

@inproceedings{aaai2022_towards_2862,
  title = {{Towards Off-Policy Learning for Ranking Policies with Logged Feedback}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/08700-towards-off-policy-learning-for-ranking-policies-with-logged-feedback/},
}

@inproceedings{aaai2024_nondbrem_6792,
  title = {{NondBREM: Nondeterministic Offline Reinforcement Learning for Large-Scale Order Dispatching}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27794},
}

@inproceedings{neurips2023_adversarial_69616,
  title = {{Adversarial Counterfactual Environment Model Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70318},
}

@inproceedings{iclr2023_extreme_32603,
  title = {{Extreme Q-Learning: MaxEnt RL without Entropy}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11367},
}

@inproceedings{icml2023_contrastive_42108,
  title = {{Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24092},
}

@inproceedings{iclr2024_consistency_35525,
  title = {{Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17548},
}

@inproceedings{iclr2024_score_35611,
  title = {{Score Regularized Policy Optimization through Diffusion Behavior}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17462},
}

@inproceedings{icml2022_phasic_41009,
  title = {{Phasic Self-Imitative Reduction for Sparse-Reward Goal-Conditioned Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17643},
}

@inproceedings{icml2023_metadiffuser_41997,
  title = {{MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24216},
}

@inproceedings{icml2024_offline_45594,
  title = {{Offline Actor-Critic Reinforcement Learning Scales to Large Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32858},
}

@inproceedings{aaai2025_active_8013,
  title = {{Active Reinforcement Learning Strategies for Offline Policy Improvement}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33803},
}

@inproceedings{aaai2025_entropy_9000,
  title = {{Entropy Regularized Task Representation Learning for Offline Meta-Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34160},
}

@inproceedings{icml2024_atradiff_45188,
  title = {{ATraDiff: Accelerating Online Reinforcement Learning with Imaginary Trajectories}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33264},
}

@inproceedings{neurips2024_epicare_73075,
  title = {{EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97595},
}

@inproceedings{neurips2025_reinforcement_77782,
  title = {{Reinforcement Learning with Action Chunking}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=XUks1Y96NR},
}

@inproceedings{iclr2025_adding_83730,
  title = {{Adding Conditional Control to Diffusion Models with Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28089},
}

@inproceedings{aaai2025_mgda_9847,
  title = {{MGDA: Model-based Goal Data Augmentation for Offline Goal-conditioned Weighted Supervised Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33999},
}

@inproceedings{icml2024_plandq_43287,
  title = {{PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35165},
}

@inproceedings{icml2024_causal_43541,
  title = {{Causal Action Influence Aware Counterfactual Data Augmentation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34911},
}

@inproceedings{icml2024_didi_43593,
  title = {{DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34859},
}

@inproceedings{icml2024_debiased_43744,
  title = {{Debiased Offline Representation Learning for Fast Online Adaptation in Non-stationary Dynamics}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34708},
}

@inproceedings{icml2024_energy_45080,
  title = {{Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33372},
}

@inproceedings{icml2024_efficient_45217,
  title = {{Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33235},
}

@inproceedings{icml2025_meta_46254,
  title = {{Meta-Black-Box-Optimization through Offline Q-function Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46306},
}

@inproceedings{icml2025_adaptive_46917,
  title = {{Adaptive Learn-then-Test: Statistically Valid and Efficient Hyperparameter Selection}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45663},
}

@inproceedings{icml2025_flow_46943,
  title = {{Flow Q-Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45637},
}