% Key papers for Importance-weighted OPE estimators (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2018_breaking_56926,
  title = {{Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11523},
}

@inproceedings{icml2016_doubly_35804,
  title = {{Doubly Robust Off-policy Value Evaluation for Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/jiang16.html},
}

@inproceedings{icml2016_data_35785,
  title = {{Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/thomasa16.html},
}

@inproceedings{neurips2017_off_56522,
  title = {{Off-policy evaluation for slate recommendation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9146},
}

@inproceedings{icml2019_cab_37202,
  title = {{CAB: Continuous Adaptive Blending for Policy Evaluation and Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4208},
}

@inproceedings{iclr2020_doubly_29592,
  title = {{Doubly Robust Bias Reduction in Infinite Horizon Off-Policy Estimation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=S1glGANtDr},
}

@inproceedings{neurips2019_off_58701,
  title = {{Off-Policy Evaluation via Off-Policy Classification}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13675},
}

@inproceedings{icml2020_minimax_38456,
  title = {{Minimax Weight and Q-Function Learning for Off-Policy Evaluation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5860},
}

@inproceedings{neurips2020_off_60450,
  title = {{Off-Policy Evaluation via the Regularized Lagrangian}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18037},
}

@inproceedings{neurips2020_off_60453,
  title = {{Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17468},
}

@inproceedings{neurips2020_coindice_59545,
  title = {{CoinDICE: Off-Policy Confidence Interval Estimation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17909},
}

@inproceedings{icml2019_more_37552,
  title = {{More Efficient Off-Policy Evaluation through Regularized Targeted Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4251},
}

@inproceedings{neurips2020_confounding_59569,
  title = {{Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17255},
}

@inproceedings{neurips2019_semi_58974,
  title = {{Semi-Parametric Efficient Policy Learning with Continuous Actions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14412},
}

@inproceedings{neurips2020_minimax_60325,
  title = {{Minimax Value Interval for Off-Policy Evaluation and Policy Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17251},
}

@inproceedings{icml2020_interpretable_38336,
  title = {{Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6723},
}

@inproceedings{iclr2020_black_29600,
  title = {{Black-box Off-policy Estimation for Infinite-Horizon Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=S1ltg1rFDS},
}

@inproceedings{icml2018_more_36858,
  title = {{More Robust Doubly Robust Off-policy Evaluation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2068},
}

@inproceedings{icml2019_combining_37229,
  title = {{Combining parametric and nonparametric models for off-policy evaluation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4093},
}

@inproceedings{icml2021_bootstrapping_39109,
  title = {{Bootstrapping Fitted Q-Evaluation for Off-Policy Inference}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8507},
}

@inproceedings{aaai2024_distributional_5724,
  title = {{Distributional Off-Policy Evaluation for Slate Recommendations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28667},
}

@inproceedings{aaai2025_cross_8567,
  title = {{Cross-Validated Off-Policy Evaluation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33765},
}

@inproceedings{neurips2024_two_71722,
  title = {{Two-way Deconfounder for Off-policy Evaluation in Causal Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95564},
}

@inproceedings{neurips2024_abstract_73013,
  title = {{Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94409},
}

@inproceedings{neurips2024_logarithmic_74632,
  title = {{Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/92960},
}

@inproceedings{iclr2024_kernel_35305,
  title = {{Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17768},
}

@inproceedings{iclr2024_skill_34668,
  title = {{Skill or Luck? Return Decomposition via Advantage Functions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18406},
}

@inproceedings{icml2025_demystifying_46474,
  title = {{Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46092},
}

@inproceedings{aaai2026_behaviour_106926,
  title = {{Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39278},
}

@inproceedings{icml2026_reward_54517,
  title = {{Reward Shaping Control Variates for Off-Policy Evaluation Under Sparse Rewards}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=potpaozpjv},
}

@inproceedings{neurips2025_simultaneous_75727,
  title = {{Simultaneous Statistical Inference for Off-Policy Evaluation in Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=BM1GqmkEHS},
}

@inproceedings{iclr2025_potec_81789,
  title = {{POTEC: Off-Policy Contextual Bandits for Large Action Spaces via Policy Decomposition}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29991},
}

@inproceedings{neurips2026_error_89739,
  title = {{Error-Guided Bellman Calibration for Semi-Offline Value Estimation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/149993},
}

@inproceedings{neurips2026_variational_90733,
  title = {{Variational Approach to Optimal IPS Estimator for Multi-logger Off-Policy Evaluation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/155166},
}

@inproceedings{neurips2026_budgeted_92491,
  title = {{Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/155643},
}