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

@inproceedings{neurips2019_towards_59105,
  title = {{Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13999},
}

@inproceedings{icml2018_scalable_36973,
  title = {{Scalable Bilinear Pi Learning Using State and Action Features}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2330},
}

@inproceedings{aaai2022_achieving_1698,
  title = {{Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/03682-achieving-zero-constraint-violation-for-constrained-reinforcement-learning-via-primal-dual-approach/},
}

@inproceedings{neurips2021_near_62027,
  title = {{Near-Optimal Offline Reinforcement Learning via Double Variance Reduction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28352},
}

@inproceedings{aaai2016_compressed_105132,
  title = {{Compressed Conditional Mean Embeddings for Model-Based Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10304},
}

@inproceedings{icml2020_efficiently_38154,
  title = {{Efficiently Solving MDPs with Stochastic Mirror Descent}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6820},
}

@inproceedings{aaai2016_generalized_105055,
  title = {{Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10227},
}

@inproceedings{icml2021_exponential_39321,
  title = {{Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8421},
}

@inproceedings{aaai2021_learning_931,
  title = {{Learning with Safety Constraints: Sample Complexity of Reinforcement Learning for Constrained MDPs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/07667-learning-with-safety-constraints-sample-complexity-of-reinforcement-learning-for-constrained-mdps/},
}

@inproceedings{icml2020_minimax_38457,
  title = {{Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6543},
}

@inproceedings{neurips2019_almost_57889,
  title = {{Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13690},
}

@inproceedings{aaai2016_incremental_105139,
  title = {{Incremental Stochastic Factorization for Online Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10311},
}

@inproceedings{neurips2022_dope_65047,
  title = {{DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53063},
}

@inproceedings{neurips2018_representation_57571,
  title = {{Representation Balancing MDPs for Off-policy Policy Evaluation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11272},
}

@inproceedings{neurips2020_efficient_59772,
  title = {{Efficient Planning in Large MDPs with Weak Linear Function Approximation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/19044},
}

@inproceedings{icml2022_independent_40697,
  title = {{Independent Policy Gradient for Large-Scale Markov Potential Games: Sharper Rates, Function Approximation, and Game-Agnostic Convergence}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/18061},
}

@inproceedings{aaai2016_randomised_105355,
  title = {{Randomised Procedures for Initialising and Switching Actions in Policy Iteration}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10408},
}

@inproceedings{icml2020_structured_38814,
  title = {{Structured Policy Iteration for Linear Quadratic Regulator}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6371},
}

@inproceedings{neurips2021_reward_61871,
  title = {{Reward-Free Model-Based Reinforcement Learning with Linear Function Approximation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26093},
}

@inproceedings{neurips2021_nearly_62674,
  title = {{Nearly Horizon-Free Offline Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28555},
}

@inproceedings{icml2025_overcoming_47789,
  title = {{Overcoming the Curse of Dimensionality in Reinforcement Learning Through Approximate Factorization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44811},
}

@inproceedings{icml2024_a_44427,
  title = {{A Primal-Dual Algorithm for Offline Constrained Reinforcement Learning with Linear MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34025},
}

@inproceedings{neurips2024_near_70171,
  title = {{Near-Optimal Distributionally Robust Reinforcement Learning with General \$L\_p\$ Norms}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96912},
}

@inproceedings{neurips2024_sample_70238,
  title = {{Sample-Efficient Constrained Reinforcement Learning with General Parameterization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96849},
}

@inproceedings{neurips2024_finding_71413,
  title = {{Finding good policies in average-reward Markov Decision Processes without prior knowledge}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95839},
}

@inproceedings{neurips2025_optimal_76758,
  title = {{Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=MjOf5qnEX7},
}

@inproceedings{icml2024_target_44391,
  title = {{Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34061},
}

@inproceedings{icml2024_model_44698,
  title = {{Model-Free Robust \$phi\$-Divergence Reinforcement Learning Using Both Offline and Online Data}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33754},
}

@inproceedings{icml2024_improving_44718,
  title = {{Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33734},
}

@inproceedings{icml2024_minimally_44733,
  title = {{Minimally Modifying a Markov Game to Achieve Any Nash Equilibrium and Value}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33719},
}

@inproceedings{icml2025_adaptive_45991,
  title = {{Adaptive Exploration for Multi-Reward Multi-Policy Evaluation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46555},
}

@inproceedings{icml2025_multiple_46298,
  title = {{Multiple-policy Evaluation via Density Estimation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46262},
}

@inproceedings{icml2025_robust_46709,
  title = {{Robust Offline Reinforcement Learning with Linearly Structured \$f\$-Divergence Regularization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45863},
}

@inproceedings{icml2025_a_47908,
  title = {{A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44695},
}

@inproceedings{icml2025_provably_48776,
  title = {{Provably Efficient RL for Linear MDPs under Instantaneous Safety Constraints in Non-Convex Feature Spaces}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43846},
}

@inproceedings{icml2026_fast_54634,
  title = {{Fast Non-Episodic Finite-Horizon RL with K-Step Lookahead Thresholding}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=qz0ChfFkiZ},
}

@inproceedings{icml2026_impact_55218,
  title = {{Impact of Connectivity on Laplacian Representations in Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=wnfPEhGqic},
}

@inproceedings{neurips2024_learning_70382,
  title = {{Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96718},
}

@inproceedings{neurips2024_intrinsic_71803,
  title = {{Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95492},
}

@inproceedings{neurips2024_confident_72308,
  title = {{Confident Natural Policy Gradient for Local Planning in \$q\_pi\$-realizable Constrained MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95038},
}