% Key papers for Preference-based RL reward learning (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2016_model_105097,
  title = {{Model-Free Preference-Based Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10269},
}

@inproceedings{neurips2020_preference_60608,
  title = {{Preference-based Reinforcement Learning with Finite-Time Guarantees}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18267},
}

@inproceedings{neurips2023_direct_67486,
  title = {{Direct Preference-based Policy Optimization without Reward Modeling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72248},
}

@inproceedings{aaai2024_can_5373,
  title = {{Can You Rely on Synthetic Labellers in Preference-Based Reinforcement Learning? It’s Complicated}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28877},
}

@inproceedings{neurips2021_b_63217,
  title = {{B-Pref: Benchmarking Preference-Based Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://openreview.net/forum?id=ps95-mkHF_},
}

@inproceedings{neurips2022_meta_64807,
  title = {{Meta-Reward-Net: Implicitly Differentiable Reward Learning for Preference-based Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53089},
}

@inproceedings{neurips2024_ra_71549,
  title = {{RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95716},
}

@inproceedings{iclr2024_hindsight_34285,
  title = {{Hindsight PRIORs for Reward Learning from Human Preferences}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18790},
}

@inproceedings{iclr2024_query_34557,
  title = {{Query-Policy Misalignment in Preference-Based Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18517},
}

@inproceedings{iclr2024_provable_35460,
  title = {{Provable Offline Preference-Based Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17613},
}

@inproceedings{iclr2024_provable_35656,
  title = {{Provable Reward-Agnostic Preference-Based Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17417},
}

@inproceedings{icml2024_rime_43748,
  title = {{RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34704},
}

@inproceedings{icml2024_listwise_44033,
  title = {{Listwise Reward Estimation for Offline Preference-based Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34419},
}

@inproceedings{icml2025_clarify_48943,
  title = {{CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43680},
}

@inproceedings{icml2026_video_50832,
  title = {{Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=G8LVO5easu},
}

@inproceedings{icml2026_paws_51054,
  title = {{PAWS: Preference Learning with Advantage-Weighted Segments}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=IPeIlnJzYa},
}

@inproceedings{icml2026_from_54754,
  title = {{From Reward-Free Representations to Preferences: Rethinking Offline Preference-Based Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=sGOmm03F40},
}

@inproceedings{neurips2025_improving_75549,
  title = {{Improving Reward Models with Proximal Policy Exploration for Preference-Based Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=9KIvyH3L7c},
}

@inproceedings{neurips2025_star_75968,
  title = {{STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=E9EwDc45f8},
}

@inproceedings{neurips2025_stair_77672,
  title = {{STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=WI8rrwYJdT},
}

@inproceedings{neurips2025_uncertainty_79333,
  title = {{Uncertainty-aware Preference Alignment for Diffusion Policies}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=oG1CIBWQ77},
}

@inproceedings{iclr2024_flow_33963,
  title = {{Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory Generation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19112},
}

@inproceedings{iclr2025_a_82134,
  title = {{A Distributional Approach to Uncertainty-Aware Preference Alignment Using Offline Demonstrations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29655},
}

@inproceedings{iclr2026_offline_85041,
  title = {{Offline Preference-Based Value Optimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=9cUdn8GKId},
}

@inproceedings{iclr2026_policy_85806,
  title = {{Policy Likelihood-based Query Sampling and Critic-Exploited Reset for Efficient Preference-based Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=ITeuGb2bYg},
}