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

@inproceedings{aaai2018_deep_102427,
  title = {{Deep Reinforcement Learning That Matters}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11694},
}

@inproceedings{aaai2018_deep_102490,
  title = {{Deep Q-learning From Demonstrations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11757},
}

@inproceedings{iclr2020_model_29603,
  title = {{Model Based Reinforcement Learning for Atari}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=S1xCPJHtDB},
}

@inproceedings{icml2017_robust_36369,
  title = {{Robust Adversarial Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/754},
}

@inproceedings{cvpr2020_end_15477,
  title = {{End-to-End Model-Free Reinforcement Learning for Urban Driving Using Implicit Affordances}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{aaai2020_exploratory_101863,
  title = {{Exploratory Combinatorial Optimization with Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5723},
}

@inproceedings{aaai2021_dear_352,
  title = {{DEAR: Deep Reinforcement Learning for Online Advertising Impression in Recommender Systems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/00750-dear-deep-reinforcement-learning-for-online-advertising-impression-in-recommender-systems/},
}

@inproceedings{icml2018_programmatically_36935,
  title = {{Programmatically Interpretable Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2203},
}

@inproceedings{iclr2020_adversarial_29456,
  title = {{Adversarial Policies: Attacking Deep Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=HJgEMpVFwB},
}

@inproceedings{aaai2020_proximal_101868,
  title = {{Proximal Distilled Evolutionary Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5728},
}

@inproceedings{iclr2018_leave_28592,
  title = {{Leave no Trace: Learning to Reset for Safe and Autonomous Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/118},
}

@inproceedings{neurips2019_learning_58503,
  title = {{Learning Reward Machines for Partially Observable Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14637},
}

@inproceedings{aaai2018_a_101286,
  title = {{A Low-Cost Ethics Shaping Approach for Designing Reinforcement Learning Agents}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11498},
}

@inproceedings{neurips2019_generalization_58323,
  title = {{Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14324},
}

@inproceedings{aaai2023_safe_4601,
  title = {{Safe Reinforcement Learning via Shielding under Partial Observability}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26723},
}

@inproceedings{iclr2019_environment_29221,
  title = {{Environment Probing Interaction Policies}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/915},
}

@inproceedings{aaai2020_hierarchical_103090,
  title = {{Hierarchical Reinforcement Learning for Open-Domain Dialog}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6400},
}

@inproceedings{iclr2021_modelling_30581,
  title = {{Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2720},
}

@inproceedings{iclr2020_single_29777,
  title = {{Single Episode Policy Transfer in Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rJeQoCNYDS},
}

@inproceedings{icml2020_cautious_38007,
  title = {{Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6633},
}

@inproceedings{neurips2025_gymnasium_79537,
  title = {{Gymnasium: A Standard Interface for Reinforcement Learning Environments}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=qPMLvJxtPK},
}

@inproceedings{aaai2025_pareto_10270,
  title = {{Pareto Set Learning for Multi-Objective Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34068},
}

@inproceedings{neurips2024_reinforcement_73535,
  title = {{Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93943},
}

@inproceedings{aaai2024_active_5117,
  title = {{Active Reinforcement Learning for Robust Building Control}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30219},
}

@inproceedings{aaai2024_get_6137,
  title = {{Get a Head Start: On-Demand Pedagogical Policy Selection in Intelligent Tutoring}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29102},
}

@inproceedings{neurips2024_model_71602,
  title = {{Model-Based Transfer Learning for Contextual Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95669},
}

@inproceedings{aaai2025_rllte_10449,
  title = {{RLLTE: Long-Term Evolution Project of Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35378},
}

@inproceedings{cvpr2024_regularized_24609,
  title = {{Regularized Parameter Uncertainty for Improving Generalization in Reinforcement Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30241},
}

@inproceedings{neurips2024_reinforcement_74447,
  title = {{Reinforcement Learning with Lookahead Information}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93125},
}

@inproceedings{aaai2025_guaranteeing_9375,
  title = {{Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33357},
}

@inproceedings{iclr2024_true_34972,
  title = {{True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18102},
}

@inproceedings{icml2024_end_43251,
  title = {{End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35201},
}

@inproceedings{neurips2024_reward_71079,
  title = {{Reward Machines for Deep RL in Noisy and Uncertain Environments}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96134},
}

@inproceedings{neurips2024_rl_71670,
  title = {{RL-GPT: Integrating Reinforcement Learning and Code-as-policy}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95611},
}

@inproceedings{iclr2024_open_35191,
  title = {{Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17882},
}

@inproceedings{icml2024_code_43529,
  title = {{Code as Reward: Empowering Reinforcement Learning with VLMs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34923},
}

@inproceedings{icml2024_in_45163,
  title = {{In-Context Decision Transformer: Reinforcement Learning via Hierarchical Chain-of-Thought}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33289},
}

@inproceedings{neurips2024_policy_71140,
  title = {{Policy Learning from Tutorial Books via Understanding, Rehearsing and Introspecting}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96082},
}

@inproceedings{neurips2024_from_71751,
  title = {{From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95538},
}

@inproceedings{neurips2025_raw2drive_75805,
  title = {{Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=CAz7UGRdLs},
}