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

@inproceedings{iclr2017_third_28197,
  title = {{Third Person Imitation Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=B16dGcqlx},
}

@inproceedings{aaai2019_virtual_101704,
  title = {{Virtual-Taobao: Virtualizing Real-World Online Retail Environment for Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4419},
}

@inproceedings{aaai2020_task_103197,
  title = {{Task-Oriented Dialog Systems That Consider Multiple Appropriate Responses under the Same Context}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6507},
}

@inproceedings{iclr2019_neural_28777,
  title = {{Neural Probabilistic Motor Primitives for Humanoid Control}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/684},
}

@inproceedings{icml2017_deeply_36141,
  title = {{Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/709},
}

@inproceedings{icml2018_policy_36924,
  title = {{Policy Optimization with Demonstrations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/1956},
}

@inproceedings{aaai2020_generative_100283,
  title = {{Generative Adversarial Regularized Mutual Information Policy Gradient Framework for Automatic Diagnosis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5456},
}

@inproceedings{aaai2020_reinforcement_102091,
  title = {{Reinforcement Learning from Imperfect Demonstrations under Soft Expert Guidance}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5953},
}

@inproceedings{neurips2018_learning_57297,
  title = {{Learning Task Specifications from Demonstrations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11524},
}

@inproceedings{neurips2018_reward_57582,
  title = {{Reward learning from human preferences and demonstrations in Atari}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11768},
}

@inproceedings{neurips2019_goal_58343,
  title = {{Goal-conditioned Imitation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14430},
}

@inproceedings{neurips2020_bail_59419,
  title = {{BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18290},
}

@inproceedings{icml2018_hierarchical_36733,
  title = {{Hierarchical Imitation and Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2290},
}

@inproceedings{iclr2021_learning_30663,
  title = {{Learning to Reach Goals via Iterated Supervised Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2574},
}

@inproceedings{aaai2023_reinforcement_4501,
  title = {{Reinforcement Learning for Branch-and-Bound Optimisation Using Retrospective Trajectories}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25521},
}

@inproceedings{neurips2020_an_59372,
  title = {{An Imitation from Observation Approach to Transfer Learning with Dynamics Mismatch}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18343},
}

@inproceedings{aaai2019_hybrid_101565,
  title = {{Hybrid Reinforcement Learning with Expert State Sequences}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4259},
}

@inproceedings{icml2023_jump_41484,
  title = {{Jump-Start Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/23897},
}

@inproceedings{neurips2024_baku_74275,
  title = {{BAKU: An Efficient Transformer for Multi-Task Policy Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93282},
}

@inproceedings{iclr2018_reinforcement_28718,
  title = {{Reinforcement Learning on Web Interfaces using Workflow-Guided Exploration}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/28},
}

@inproceedings{aaai2024_no_6780,
  title = {{No Prior Mask: Eliminate Redundant Action for Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29652},
}

@inproceedings{aaai2024_rlfold_7057,
  title = {{RLfOLD: Reinforcement Learning from Online Demonstrations in Urban Autonomous Driving}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29049},
}

@inproceedings{neurips2024_vision_74328,
  title = {{Vision-Language Navigation with Energy-Based Policy}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93232},
}

@inproceedings{neurips2025_resim_77362,
  title = {{ReSim: Reliable World Simulation for Autonomous Driving}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=T0CiI4gDFB},
}

@inproceedings{neurips2024_surgicai_72269,
  title = {{SurgicAI: A Hierarchical Platform for Fine-Grained Surgical Policy Learning and Benchmarking}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://openreview.net/forum?id=Sp9cj4pNYD},
}

@inproceedings{aaai2024_learning_6494,
  title = {{Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28907},
}

@inproceedings{aaai2025_sorrel_10623,
  title = {{SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33219},
}

@inproceedings{iclr2024_fourier_34559,
  title = {{Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18515},
}

@inproceedings{neurips2024_off_73559,
  title = {{Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93921},
}

@inproceedings{neurips2024_when_74231,
  title = {{When to Act and When to Ask: Policy Learning With Deferral Under Hidden Confounding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93323},
}

@inproceedings{neurips2025_adversarial_78706,
  title = {{Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=hVoIz6xD9Q},
}

@inproceedings{neurips2024_robot_71669,
  title = {{Robot Policy Learning with Temporal Optimal Transport Reward}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95612},
}

@inproceedings{neurips2024_text_73810,
  title = {{Text-Aware Diffusion for Policy Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93698},
}

@inproceedings{iclr2025_instant_83180,
  title = {{Instant Policy: In-Context Imitation Learning via Graph Diffusion}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28628},
}

@inproceedings{iclr2025_bidirectional_83572,
  title = {{Bidirectional Decoding: Improving Action Chunking via Guided Test-Time Sampling}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28245},
}

@inproceedings{aaai2025_enhancing_8983,
  title = {{Enhancing Online Reinforcement Learning with Meta-Learned Objective from Offline Data}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33784},
}

@inproceedings{aaai2025_imitation_9510,
  title = {{Imitation Learning Backoff: Reinforcement Learning-based Channel Access for Guaranteeing Fairness (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35266},
}

@inproceedings{iclr2024_dual_35633,
  title = {{Dual RL: Unification and New Methods for Reinforcement and Imitation Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17440},
}

@inproceedings{icml2024_stealthy_43973,
  title = {{Stealthy Imitation: Reward-guided Environment-free Policy Stealing}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34479},
}