% Key papers for Reward learning from demonstrations (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2020_predicting_16056,
  title = {{Predicting Goal-Directed Human Attention Using Inverse Reinforcement Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2016_showing_55992,
  title = {{Showing versus doing: Teaching by demonstration}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7429},
}

@inproceedings{neurips2020_reward_60723,
  title = {{Reward-rational (implicit) choice: A unifying formalism for reward learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18233},
}

@inproceedings{neurips2017_inverse_56397,
  title = {{Inverse Reward Design}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9444},
}

@inproceedings{aaai2018_optiongan_102508,
  title = {{OptionGAN: Learning Joint Reward-Policy Options Using Generative Adversarial Inverse Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11775},
}

@inproceedings{aaai2019_machine_103278,
  title = {{Machine Teaching for Inverse Reinforcement Learning: Algorithms and Applications}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4771},
}

@inproceedings{neurips2018_variational_57761,
  title = {{Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11816},
}

@inproceedings{aaai2023_the_4808,
  title = {{The Perils of Trial-and-Error Reward Design: Misdesign through Overfitting and Invalid Task Specifications}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25733},
}

@inproceedings{neurips2018_teaching_57677,
  title = {{Teaching Inverse Reinforcement Learners via Features and Demonstrations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11809},
}

@inproceedings{aaai2018_efficient_102488,
  title = {{Efficient Probabilistic Performance Bounds for Inverse Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11755},
}

@inproceedings{icml2019_extrapolating_37349,
  title = {{Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4186},
}

@inproceedings{neurips2018_where_57780,
  title = {{Where Do You Think You're Going?: Inferring Beliefs about Dynamics from Behavior}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11161},
}

@inproceedings{aaai2016_distance_105384,
  title = {{Distance Minimization for Reward Learning from Scored Trajectories}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10411},
}

@inproceedings{icml2019_on_37605,
  title = {{On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4315},
}

@inproceedings{iclr2021_scalable_30000,
  title = {{Scalable Bayesian Inverse Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3152},
}

@inproceedings{icml2020_intrinsic_38340,
  title = {{Intrinsic Reward Driven Imitation Learning via Generative Model}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6386},
}

@inproceedings{icml2019_learning_37496,
  title = {{Learning from a Learner}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4077},
}

@inproceedings{aaai2020_the_99988,
  title = {{The Unreasonable Effectiveness of Inverse Reinforcement Learning in Advancing Cancer Research}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5380},
}

@inproceedings{aaai2022_programmatic_2586,
  title = {{Programmatic Reward Design by Example}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/09233-programmatic-reward-design-by-example/},
}

@inproceedings{iclr2019_adversarial_28915,
  title = {{Adversarial Imitation via Variational Inverse Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/1137},
}

@inproceedings{aaai2025_inverse_9599,
  title = {{Inverse Reinforcement Learning by Estimating Expertise of Demonstrators}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33705},
}

@inproceedings{iclr2024_massively_35678,
  title = {{Massively Scalable Inverse Reinforcement Learning in Google Maps}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17395},
}

@inproceedings{icml2024_hybrid_43365,
  title = {{Hybrid Inverse Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35087},
}

@inproceedings{neurips2024_maximum_72426,
  title = {{Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94930},
}

@inproceedings{aaai2024_making_6598,
  title = {{Making AI Policies Transparent to Humans through Demonstrations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30399},
}

@inproceedings{icml2024_environment_43704,
  title = {{Environment Design for Inverse Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34748},
}

@inproceedings{icml2025_elemental_48161,
  title = {{ELEMENTAL: Interactive Learning from Demonstrations and Vision-Language Models for Reward Design in Robotics}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44449},
}

@inproceedings{icml2026_recovering_51300,
  title = {{Recovering Hidden Reward in Diffusion-Based Policies}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=KibOuVwmor},
}

@inproceedings{icml2026_distributional_52854,
  title = {{Distributional Inverse Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=ZcnZ6vs4yX},
}

@inproceedings{neurips2024_simplifying_72287,
  title = {{Simplifying Constraint Inference with Inverse Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95058},
}

@inproceedings{neurips2024_rethinking_72438,
  title = {{Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94918},
}

@inproceedings{iclr2026_learning_84753,
  title = {{Learning to Answer from Correct Demonstrations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=69fIHgLjyH},
}

@inproceedings{iclr2026_robustness_87663,
  title = {{Robustness in the Face of Partial Identifiability in Reward Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=e4xANXjA9W},
}

@inproceedings{iclr2026_grace_89075,
  title = {{GRACE: A Language Model Framework for Explainable Inverse Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=uW9FoHBuoQ},
}

@inproceedings{neurips2026_inverting_90980,
  title = {{Inverting the Bellman Equation: From \$Q\$-Values to World Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/153840},
}

@inproceedings{neurips2026_imperfect_91705,
  title = {{Imperfect World Models are Exploitable}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/154874},
}

@inproceedings{aaai2026_inferring_106515,
  title = {{Inferring Heterogeneous Private Valuations from Offline Market Data via Entropic Risk-Sensitive Utility Maximization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38822},
}

@inproceedings{aaai2026_reward_107569,
  title = {{Reward Redistribution via Gaussian Process Likelihood Estimation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39921},
}

@inproceedings{aaai2026_misalignment_108755,
  title = {{Misalignment from Treating Means as Ends}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/41107},
}

@inproceedings{iclr2024_meta_34736,
  title = {{Meta Inverse Constrained Reinforcement Learning: Convergence Guarantee and Generalization Analysis}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18338},
}