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

@inproceedings{aaai2018_safe_102530,
  title = {{Safe Reinforcement Learning via Shielding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11797},
}

@inproceedings{aaai2019_end_101522,
  title = {{End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4213},
}

@inproceedings{neurips2017_safe_56644,
  title = {{Safe Model-based Reinforcement Learning with Stability Guarantees}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8885},
}

@inproceedings{aaai2021_wcsac_1624,
  title = {{WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/10639-wcsac-worst-case-soft-actor-critic-for-safety-constrained-reinforcement-learning/},
}

@inproceedings{icml2020_responsive_38697,
  title = {{Responsive Safety in Reinforcement Learning by PID Lagrangian Methods}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6173},
}

@inproceedings{iclr2021_conservative_30555,
  title = {{Conservative Safety Critics for Exploration}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2600},
}

@inproceedings{neurips2019_convergent_58048,
  title = {{Convergent Policy Optimization for Safe Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13493},
}

@inproceedings{aaai2022_exploring_2072,
  title = {{Exploring Safer Behaviors for Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/07701-exploring-safer-behaviors-for-deep-reinforcement-learning/},
}

@inproceedings{aaai2023_evaluating_3596,
  title = {{Evaluating Model-Free Reinforcement Learning toward Safety-Critical Tasks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26786},
}

@inproceedings{aaai2019_safe_101712,
  title = {{Safe Policy Improvement with Baseline Bootstrapping in Factored Environments}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4427},
}

@inproceedings{aaai2022_conservative_1863,
  title = {{Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/05404-conservative-and-adaptive-penalty-for-model-based-safe-reinforcement-learning/},
}

@inproceedings{aaai2023_augmented_3135,
  title = {{Augmented Proximal Policy Optimization for Safe Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25888},
}

@inproceedings{neurips2022_constrained_63770,
  title = {{Constrained Update Projection Approach to Safe Policy Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54057},
}

@inproceedings{neurips2022_model_65691,
  title = {{Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithm}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55095},
}

@inproceedings{icml2021_accelerating_39008,
  title = {{Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8451},
}

@inproceedings{icml2021_crpo_39121,
  title = {{CRPO: A New Approach for Safe Reinforcement Learning with Convergence Guarantee}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8995},
}

@inproceedings{icml2022_constrained_40359,
  title = {{Constrained Variational Policy Optimization for Safe Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16641},
}

@inproceedings{neurips2020_neurosymbolic_60419,
  title = {{Neurosymbolic Reinforcement Learning with Formally Verified Exploration}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18130},
}

@inproceedings{aaai2024_balance_5269,
  title = {{Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30102},
}

@inproceedings{neurips2022_towards_65043,
  title = {{Towards Safe Reinforcement Learning with a Safety Editor Policy}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53919},
}

@inproceedings{aaai2024_safe_7248,
  title = {{Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30170},
}

@inproceedings{aaai2024_safeguarded_7250,
  title = {{Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30137},
}

@inproceedings{aaai2024_imitate_6276,
  title = {{Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29136},
}

@inproceedings{aaai2024_p2bpo_6884,
  title = {{P2BPO: Permeable Penalty Barrier-Based Policy Optimization for Safe RL}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30094},
}

@inproceedings{neurips2024_verified_74203,
  title = {{Verified Safe Reinforcement Learning for Neural Network Dynamic Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93347},
}

@inproceedings{iclr2024_physics_33640,
  title = {{Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19435},
}

@inproceedings{aaai2025_tilted_10999,
  title = {{Tilted Quantile Gradient Updates for Quantile-Constrained Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34006},
}

@inproceedings{iclr2024_safedreamer_35476,
  title = {{SafeDreamer: Safe Reinforcement Learning with World Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17597},
}

@inproceedings{iclr2024_off_35561,
  title = {{Off-Policy Primal-Dual Safe Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17512},
}

@inproceedings{icml2024_safe_43737,
  title = {{Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34715},
}

@inproceedings{icml2024_feasibility_44069,
  title = {{Feasibility Consistent Representation Learning for Safe Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34383},
}

@inproceedings{icml2025_embedding_46108,
  title = {{Embedding Safety into RL: A New Take on Trust Region Methods}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46451},
}

@inproceedings{icml2026_cspo_49595,
  title = {{CSPO: Constraint-Sensitive Policy Optimization for Safe Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=3ySR3TCMRP},
}

@inproceedings{icml2026_traces_54063,
  title = {{TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=lXnoKG4jFU},
}

@inproceedings{neurips2024_reinforcement_71768,
  title = {{Reinforcement Learning with Adaptive Regularization for Safe Control of Critical Systems}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95521},
}

@inproceedings{neurips2024_enhancing_73882,
  title = {{Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93629},
}

@inproceedings{neurips2025_a_75065,
  title = {{A Provable Approach for End-to-End Safe Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=3qDFW07Lw7},
}

@inproceedings{neurips2025_fuz_77353,
  title = {{Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=SuewCbLYBS},
}

@inproceedings{neurips2025_efficient_77986,
  title = {{Efficient Safe Meta-Reinforcement Learning: Provable Near-Optimality and Anytime Safety}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=ZtKXAbHQ43},
}