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

@inproceedings{aaai2016_rao_105365,
  title = {{RAO*: An Algorithm for Chance-Constrained POMDP's}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10423},
}

@inproceedings{aaai2019_personalized_103387,
  title = {{Personalized Robot Tutoring Using the Assistive Tutor POMDP (AT-POMDP)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4807},
}

@inproceedings{aaai2017_accelerated_106045,
  title = {{Accelerated Vector Pruning for Optimal POMDP Solvers}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11032},
}

@inproceedings{aaai2020_off_103338,
  title = {{Off-Policy Evaluation in Partially Observable Environments}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6590},
}

@inproceedings{aaai2017_dynamically_103405,
  title = {{Dynamically Constructed (PO)MDPs for Adaptive Robot Planning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11042},
}

@inproceedings{aaai2016_learning_105164,
  title = {{Learning for Decentralized Control of Multiagent Systems in Large, Partially-Observable Stochastic Environments}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10135},
}

@inproceedings{aaai2016_a_105364,
  title = {{A Symbolic SAT-Based Algorithm for Almost-Sure Reachability with Small Strategies in POMDPs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10422},
}

@inproceedings{aaai2020_point_103312,
  title = {{Point-Based Methods for Model Checking in Partially Observable Markov Decision Processes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6563},
}

@inproceedings{neurips2017_data_56228,
  title = {{Data-Efficient Reinforcement Learning in Continuous State-Action Gaussian-POMDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8992},
}

@inproceedings{aaai2016_solving_105349,
  title = {{Solving Risk-Sensitive POMDPs With and Without Cost Observations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10402},
}

@inproceedings{aaai2017_optimizing_103347,
  title = {{Optimizing Expectation with Guarantees in POMDPs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11046},
}

@inproceedings{aaai2016_target_105155,
  title = {{Target Surveillance in Adversarial Environments Using POMDPs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10126},
}

@inproceedings{aaai2023_safe_4600,
  title = {{Safe Policy Improvement for POMDPs via Finite-State Controllers}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26763},
}

@inproceedings{icml2020_information_38327,
  title = {{Information Particle Filter Tree: An Online Algorithm for POMDPs with Belief-Based Rewards on Continuous Domains}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6098},
}

@inproceedings{neurips2019_budgeted_57967,
  title = {{Budgeted Reinforcement Learning in Continuous State Space}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13969},
}

@inproceedings{iclr2020_svqn_29771,
  title = {{SVQN: Sequential Variational Soft Q-Learning Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=r1xPh2VtPB},
}

@inproceedings{neurips2018_rho_57790,
  title = {{rho-POMDPs have Lipschitz-Continuous epsilon-Optimal Value Functions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11668},
}

@inproceedings{neurips2020_sample_60777,
  title = {{Sample-Efficient Reinforcement Learning of Undercomplete POMDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18663},
}

@inproceedings{neurips2021_reinforcement_62996,
  title = {{Reinforcement Learning with State Observation Costs in Action-Contingent Noiselessly Observable Markov Decision Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26563},
}

@inproceedings{aaai2021_improved_754,
  title = {{Improved POMDP Tree Search Planning with Prioritized Action Branching}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/11888-improved-pomdp-tree-search-planning-with-prioritized-action-branching/},
}

@inproceedings{aaai2025_learning_9738,
  title = {{Learning Logic Specifications for Policy Guidance in POMDPs: an Inductive Logic Programming Approach}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35134},
}

@inproceedings{neurips2024_mitigating_72697,
  title = {{Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94689},
}

@inproceedings{aaai2024_a_5069,
  title = {{A Surprisingly Simple Continuous-Action POMDP Solver: Lazy Cross-Entropy Search Over Policy Trees}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29992},
}

@inproceedings{iclr2024_sample_33497,
  title = {{Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19578},
}

@inproceedings{icml2024_rethinking_44469,
  title = {{Rethinking Transformers in Solving POMDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33983},
}

@inproceedings{iclr2024_a_33739,
  title = {{A Policy Gradient Method for Confounded POMDPs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19336},
}

@inproceedings{icml2024_provably_43474,
  title = {{Provably Efficient Partially Observable Risk-sensitive Reinforcement Learning with Hindsight Observation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34978},
}

@inproceedings{icml2024_provable_44275,
  title = {{Provable Representation with Efficient Planning for Partially Observable Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34177},
}

@inproceedings{icml2025_pigdreamer_48484,
  title = {{PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44134},
}

@inproceedings{icml2026_the_54031,
  title = {{The Value Function Semi-Algebraic Set in Partially Observable Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=l94JabCBGL},
}

@inproceedings{neurips2024_periodic_71454,
  title = {{Periodic agent-state based Q-learning for POMDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95802},
}

@inproceedings{neurips2024_belief_73426,
  title = {{Belief-State Query Policies for User-Aligned POMDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94035},
}

@inproceedings{neurips2024_on_74135,
  title = {{On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93403},
}

@inproceedings{neurips2025_scalable_76433,
  title = {{Scalable Policy-Based RL Algorithms for POMDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=JInukYoZPI},
}

@inproceedings{neurips2025_sequential_77974,
  title = {{Sequential Monte Carlo for Policy Optimization in Continuous POMDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Zj0L8xIZYP},
}

@inproceedings{neurips2025_multi_78999,
  title = {{Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=kcmw3OH5bh},
}

@inproceedings{neurips2025_on_79046,
  title = {{On Evaluating Policies for Robust POMDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=l2Wl77TSYY},
}

@inproceedings{neurips2025_breaking_79794,
  title = {{Breaking the Order Barrier: Off-Policy Evaluation for Confounded POMDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=t3LTjkXDJA},
}

@inproceedings{iclr2025_statistical_82114,
  title = {{Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29675},
}

@inproceedings{neurips2026_multi_91297,
  title = {{Multi-Environment POMDPs with Finite-Horizon Objectives}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/155767},
}