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

@inproceedings{iclr2019_reward_29071,
  title = {{Reward Constrained Policy Optimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/756},
}

@inproceedings{aaai2020_ipo_102070,
  title = {{IPO: Interior-Point Policy Optimization under Constraints}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5932},
}

@inproceedings{icml2017_constrained_36111,
  title = {{Constrained Policy Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/848},
}

@inproceedings{iclr2020_projection_29813,
  title = {{Projection-Based Constrained Policy Optimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rke3TJrtPS},
}

@inproceedings{neurips2019_reinforcement_58904,
  title = {{Reinforcement Learning with Convex Constraints}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14334},
}

@inproceedings{aaai2020_cost_102077,
  title = {{Cost-Effective Incentive Allocation via Structured Counterfactual Inference}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5939},
}

@inproceedings{neurips2020_constrained_59579,
  title = {{Constrained episodic reinforcement learning in concave-convex and knapsack settings}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18379},
}

@inproceedings{aaai2023_gradient_3790,
  title = {{Gradient-Adaptive Pareto Optimization for Constrained Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26353},
}

@inproceedings{iclr2021_balancing_30335,
  title = {{Balancing Constraints and Rewards with Meta-Gradient D4PG}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2639},
}

@inproceedings{icml2022_reachability_41068,
  title = {{Reachability Constrained Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/18133},
}

@inproceedings{aaai2023_achieving_3060,
  title = {{Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Conservative Natural Policy Gradient Primal-Dual Algorithm}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25826},
}

@inproceedings{aaai2024_enhancing_5856,
  title = {{Enhancing Off-Policy Constrained Reinforcement Learning through Adaptive Ensemble C Estimation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30177},
}

@inproceedings{icml2023_reload_41687,
  title = {{ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24094},
}

@inproceedings{aaai2023_constrained_3311,
  title = {{Constrained Reinforcement Learning in Hard Exploration Problems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26757},
}

@inproceedings{icml2022_direct_40455,
  title = {{Direct Behavior Specification via Constrained Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16263},
}

@inproceedings{neurips2022_policy_66466,
  title = {{Policy Optimization with Linear Temporal Logic Constraints}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53437},
}

@inproceedings{aaai2024_reward_7157,
  title = {{Reward Penalties on Augmented States for Solving Richly Constrained RL Effectively}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29962},
}

@inproceedings{icml2021_density_39228,
  title = {{Density Constrained Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8985},
}

@inproceedings{icml2021_shortest_39944,
  title = {{Shortest-Path Constrained Reinforcement Learning for Sparse Reward Tasks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/9117},
}

@inproceedings{neurips2022_quantile_64704,
  title = {{Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probability}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53797},
}

@inproceedings{neurips2024_autoregressive_73384,
  title = {{Autoregressive Policy Optimization for Constrained Allocation Tasks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94070},
}

@inproceedings{neurips2025_chpo_76525,
  title = {{CHPO: Constrained Hybrid-action Policy Optimization for Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=KMaBmPHkVj},
}

@inproceedings{iclr2025_conflict_83479,
  title = {{Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28337},
}

@inproceedings{aaai2026_proactive_107626,
  title = {{Proactive Constrained Policy Optimization with Preemptive Penalty}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39978},
}

@inproceedings{aaai2025_augmented_8182,
  title = {{Augmented Lagrangian Risk-constrained Reinforcement Learning for Portfolio Optimization (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35252},
}

@inproceedings{aaai2025_leveraging_9776,
  title = {{Leveraging Constraint Violation Signals for Action Constrained Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33714},
}

@inproceedings{icml2024_constrained_43956,
  title = {{Constrained Reinforcement Learning Under Model Mismatch}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34496},
}

@inproceedings{icml2024_acpo_44917,
  title = {{ACPO: A Policy Optimization Algorithm for Average MDPs with Constraints}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33535},
}

@inproceedings{icml2025_extreme_46019,
  title = {{Extreme Value Policy Optimization for Safe Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46527},
}

@inproceedings{icml2025_controlling_48524,
  title = {{Controlling Underestimation Bias in Constrained Reinforcement Learning for Safe Exploration}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44096},
}

@inproceedings{icml2026_stochastic_51983,
  title = {{Stochastic Minimum-Cost Reach-Avoid Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=ReCCYnyfXa},
}

@inproceedings{neurips2024_last_70308,
  title = {{Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96786},
}

@inproceedings{neurips2024_deterministic_72687,
  title = {{Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94698},
}

@inproceedings{neurips2025_risk_80162,
  title = {{Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=wrFaF1gA6R},
}

@inproceedings{iclr2026_dual_84333,
  title = {{Dual-Objective Reinforcement Learning with Novel Hamilton-Jacobi-Bellman Formulations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=1SdPgRQrr5},
}

@inproceedings{iclr2026_accelerated_89499,
  title = {{Accelerated Learning with Linear Temporal Logic using Differentiable Simulation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=zbdhhlIy8o},
}

@inproceedings{neurips2026_global_91185,
  title = {{Global Optimality for Constrained Exploration via Penalty Regularization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/152447},
}

@inproceedings{neurips2026_decoupling_95567,
  title = {{Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/154428},
}