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

@inproceedings{neurips2018_is_57252,
  title = {{Is Q-Learning Provably Efficient?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11477},
}

@inproceedings{icml2020_provably_38656,
  title = {{Provably Efficient Exploration in Policy Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5993},
}

@inproceedings{icml2020_reward_38706,
  title = {{Reward-Free Exploration for Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6285},
}

@inproceedings{icml2020_policy_38623,
  title = {{Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5957},
}

@inproceedings{iclr2022_understanding_31308,
  title = {{Understanding Domain Randomization for Sim-to-real Transfer}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6876},
}

@inproceedings{neurips2020_on_60469,
  title = {{On Reward-Free Reinforcement Learning with Linear Function Approximation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18304},
}

@inproceedings{neurips2020_pc_60557,
  title = {{PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18445},
}

@inproceedings{aaai2016_efficient_105113,
  title = {{Efficient Average Reward Reinforcement Learning Using Constant Shifting Values}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10285},
}

@inproceedings{neurips2017_finite_56320,
  title = {{Finite Sample Analysis of the GTD Policy Evaluation Algorithms in Markov Setting}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9325},
}

@inproceedings{neurips2019_near_58656,
  title = {{Near-Optimal Reinforcement Learning in Dynamic Treatment Regimes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14279},
}

@inproceedings{icml2019_policy_37657,
  title = {{Policy Certificates: Towards Accountable Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3749},
}

@inproceedings{neurips2020_task_60920,
  title = {{Task-agnostic Exploration in Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17826},
}

@inproceedings{neurips2021_policy_62026,
  title = {{Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26797},
}

@inproceedings{aaai2018_pac_102327,
  title = {{PAC Reinforcement Learning With an Imperfect Model}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11594},
}

@inproceedings{neurips2022_unpacking_64316,
  title = {{Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/52963},
}

@inproceedings{icml2020_clinician_38015,
  title = {{Clinician-in-the-Loop Decision Making: Reinforcement Learning with Near-Optimal Set-Valued Policies}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5797},
}

@inproceedings{neurips2024_overcoming_71568,
  title = {{Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95701},
}

@inproceedings{aaai2021_temple_1474,
  title = {{TempLe: Learning Template of Transitions for Sample Efficient Multi-task RL}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/09765-temple-learning-template-of-transitions-for-sample-efficient-multi-task-rl/},
}

@inproceedings{neurips2020_is_60113,
  title = {{Is Long Horizon RL More Difficult Than Short Horizon RL?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17505},
}

@inproceedings{icml2017_fairness_36188,
  title = {{Fairness in Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/697},
}

@inproceedings{iclr2025_asynchronous_80809,
  title = {{Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30959},
}

@inproceedings{iclr2024_finite_33920,
  title = {{Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19155},
}

@inproceedings{neurips2024_federated_71135,
  title = {{Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96087},
}

@inproceedings{iclr2024_the_33641,
  title = {{The Effective Horizon Explains Deep RL Performance in Stochastic Environments}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19434},
}

@inproceedings{icml2024_uncertainty_43746,
  title = {{Uncertainty-Aware Reward-Free Exploration with General Function Approximation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34706},
}

@inproceedings{icml2024_federated_44149,
  title = {{Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34303},
}

@inproceedings{icml2025_learning_47905,
  title = {{Learning Policy Committees for Effective Personalization in MDPs with Diverse Tasks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44698},
}

@inproceedings{icml2026_constrained_49649,
  title = {{Constrained Meta Reinforcement Learning with Provable Test-Time Safety}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=4OFXgDuRNH},
}

@inproceedings{icml2026_bilevel_50997,
  title = {{Bilevel Optimization over Saddle Points of Zero-Sum Markov Games}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=HtSjPOIMMc},
}

@inproceedings{icml2026_when_51516,
  title = {{When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=N4PZVvr8lt},
}

@inproceedings{icml2026_online_53447,
  title = {{Online Robust Reinforcement Learning with General Function Approximation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=fcVsVQkjIc},
}

@inproceedings{icml2026_reinforcement_53557,
  title = {{Reinforcement Learning for Reachability: Guaranteeing Asymptotic Optimality}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=ga20H0vR6f},
}

@inproceedings{neurips2024_how_72780,
  title = {{How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94615},
}

@inproceedings{neurips2024_hybrid_72928,
  title = {{Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94483},
}

@inproceedings{neurips2024_policy_73908,
  title = {{Policy Mirror Descent with Lookahead}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93603},
}

@inproceedings{neurips2025_exploration_75622,
  title = {{Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=A5Y8Uh5Szl},
}

@inproceedings{iclr2026_a_85546,
  title = {{A Unifying View of Coverage in Linear Off-policy Evaluation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=FjTYIRufJp},
}

@inproceedings{neurips2026_fast_94915,
  title = {{Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/149055},
}

@inproceedings{icml2024_reward_44372,
  title = {{Reward-Free Kernel-Based Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34080},
}