% Key papers for Regret bounds with function approximation (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2020_model_38462,
  title = {{Model-Based Reinforcement Learning with Value-Targeted Regression}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6705},
}

@inproceedings{icml2019_tighter_37805,
  title = {{Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4172},
}

@inproceedings{icml2019_politex_37641,
  title = {{POLITEX: Regret Bounds for Policy Iteration using Expert Prediction}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3753},
}

@inproceedings{icml2017_minimax_36286,
  title = {{Minimax Regret Bounds for Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/774},
}

@inproceedings{iclr2020_q_29344,
  title = {{Q-learning with UCB Exploration is Sample Efficient for Infinite-Horizon MDP}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=BkglSTNFDB},
}

@inproceedings{icml2017_why_36457,
  title = {{Why is Posterior Sampling Better than Optimism for Reinforcement Learning?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/589},
}

@inproceedings{neurips2019_provably_58849,
  title = {{Provably Efficient Q-Learning with Low Switching Cost}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13875},
}

@inproceedings{neurips2019_non_58681,
  title = {{Non-Asymptotic Gap-Dependent Regret Bounds for Tabular MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13338},
}

@inproceedings{neurips2020_risk_60727,
  title = {{Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18597},
}

@inproceedings{icml2021_logarithmic_39574,
  title = {{Logarithmic Regret for Reinforcement Learning with Linear Function Approximation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/10521},
}

@inproceedings{neurips2020_dynamic_59749,
  title = {{Dynamic Regret of Policy Optimization in Non-Stationary Environments}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18121},
}

@inproceedings{neurips2019_worst_59206,
  title = {{Worst-Case Regret Bounds for Exploration via Randomized Value Functions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14362},
}

@inproceedings{icml2021_model_39618,
  title = {{Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8593},
}

@inproceedings{neurips2019_information_58412,
  title = {{Information-Theoretic Confidence Bounds for Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13439},
}

@inproceedings{neurips2021_breaking_62474,
  title = {{Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28441},
}

@inproceedings{icml2021_ucb_40066,
  title = {{UCB Momentum Q-learning: Correcting the bias without forgetting}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8561},
}

@inproceedings{neurips2021_exponential_61862,
  title = {{Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28235},
}

@inproceedings{icml2021_near_39650,
  title = {{Near-Optimal Model-Free Reinforcement Learning in Non-Stationary Episodic MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8427},
}

@inproceedings{neurips2017_online_56551,
  title = {{Online Reinforcement Learning in Stochastic Games}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9275},
}

@inproceedings{neurips2019_regret_58897,
  title = {{Regret Minimization for Reinforcement Learning by Evaluating the Optimal Bias Function}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13468},
}

@inproceedings{aaai2024_dynamic_5768,
  title = {{Dynamic Regret of Adversarial MDPs with Unknown Transition and Linear Function Approximation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29261},
}

@inproceedings{icml2024_provably_44943,
  title = {{Provably Efficient Exploration in Quantum Reinforcement Learning with Logarithmic Worst-Case Regret}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33509},
}

@inproceedings{neurips2024_near_71689,
  title = {{Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95594},
}

@inproceedings{iclr2024_horizon_34708,
  title = {{Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18366},
}

@inproceedings{icml2024_eluder_43418,
  title = {{Eluder-based Regret for Stochastic Contextual MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35034},
}

@inproceedings{icml2024_reinforcement_44547,
  title = {{Reinforcement Learning and Regret Bounds for Admission Control}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33905},
}

@inproceedings{icml2024_near_45061,
  title = {{Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33391},
}

@inproceedings{icml2026_near_49783,
  title = {{Near-Optimal Regret for Policy Optimization in Contextual MDPs with General Offline Function Approximation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=5faxBOZAmW},
}

@inproceedings{icml2026_posterior_51944,
  title = {{Posterior Sampling Reinforcement Learning with Gaussian Processes for Continuous Control: Sublinear Regret Bounds for Unbounded State Spaces}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=RKVsEuwbJ0},
}

@inproceedings{neurips2024_uniform_71524,
  title = {{Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95739},
}

@inproceedings{neurips2025_optimal_78247,
  title = {{Optimal Regret Bounds via Low-Rank Structured Variation in Non-Stationary Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=ccHq9OScXW},
}

@inproceedings{neurips2025_eluder_78390,
  title = {{Eluder dimension: localise it!}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=e8R0ytPhLv},
}

@inproceedings{neurips2025_sharp_79469,
  title = {{Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=phC2nmJywQ},
}

@inproceedings{iclr2025_gap_80908,
  title = {{Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30859},
}

@inproceedings{iclr2026_q_87763,
  title = {{Q-Learning with Fine-Grained Gap-Dependent Regret}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=fE0RJto3Na},
}

@inproceedings{iclr2026_an_88331,
  title = {{An Improved Model-free Decision-estimation Coefficient with Applications in Adversarial MDPs}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=lbLAgGF8OO},
}

@inproceedings{icml2025_position_46031,
  title = {{Position: Constants are Critical in Regret Bounds for Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/40179},
}

@inproceedings{icml2025_online_46155,
  title = {{Online Learning in Risk Sensitive constrained MDP}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46405},
}

@inproceedings{icml2025_policy_48028,
  title = {{Policy-Regret Minimization in Markov Games with Function Approximation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44578},
}

@inproceedings{icml2025_minimax_48556,
  title = {{Minimax Optimal Regret Bound for Reinforcement Learning with Trajectory Feedback}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44065},
}