% Key papers for Average-reward and regularized MDPs (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2016_reinforcement_105054,
  title = {{Reinforcement Learning with Parameterized Actions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10226},
}

@inproceedings{icml2019_a_37112,
  title = {{A Theory of Regularized Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4025},
}

@inproceedings{neurips2019_rudder_58871,
  title = {{RUDDER: Return Decomposition for Delayed Rewards}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14291},
}

@inproceedings{aaai2020_scalable_103313,
  title = {{Scalable Methods for Computing State Similarity in Deterministic Markov Decision Processes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6564},
}

@inproceedings{aaai2020_being_102008,
  title = {{Being Optimistic to Be Conservative: Quickly Learning a CVaR Policy}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5870},
}

@inproceedings{aaai2019_state_101492,
  title = {{State Abstraction as Compression in Apprenticeship Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4179},
}

@inproceedings{neurips2020_model_60341,
  title = {{Model-based Reinforcement Learning for Semi-Markov Decision Processes with Neural ODEs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17959},
}

@inproceedings{aaai2019_rethinking_103302,
  title = {{Rethinking the Discount Factor in Reinforcement Learning: A Decision Theoretic Approach}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4795},
}

@inproceedings{neurips2019_non_58684,
  title = {{Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13813},
}

@inproceedings{aaai2021_lipschitz_938,
  title = {{Lipschitz Lifelong Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/08270-lipschitz-lifelong-reinforcement-learning/},
}

@inproceedings{aaai2019_quota_101812,
  title = {{QUOTA: The Quantile Option Architecture for Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4527},
}

@inproceedings{icml2020_optimizing_38601,
  title = {{Optimizing for the Future in Non-Stationary MDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6316},
}

@inproceedings{neurips2022_learning_64695,
  title = {{Learning to Branch with Tree MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53321},
}

@inproceedings{icml2021_learning_39540,
  title = {{Learning and Planning in Average-Reward Markov Decision Processes}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/10105},
}

@inproceedings{icml2020_provable_38651,
  title = {{Provable Representation Learning for Imitation Learning via Bi-level Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6457},
}

@inproceedings{neurips2019_a_57834,
  title = {{A Regularized Approach to Sparse Optimal Policy in Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13714},
}

@inproceedings{icml2019_the_37797,
  title = {{The Value Function Polytope in Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4096},
}

@inproceedings{neurips2019_tight_59093,
  title = {{Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy Policies}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14608},
}

@inproceedings{aaai2022_a_1679,
  title = {{A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/03868-a-provably-efficient-model-free-algorithm-for-infinite-horizon-average-reward-constrained-markov-decision-processes/},
}

@inproceedings{neurips2019_a_57820,
  title = {{A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13695},
}

@inproceedings{aaai2024_principal_6986,
  title = {{Principal-Agent Reward Shaping in MDPs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28805},
}

@inproceedings{aaai2024_a_5050,
  title = {{A PAC Learning Algorithm for LTL and Omega-Regular Objectives in MDPs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30148},
}

@inproceedings{aaai2024_stop_7421,
  title = {{Stop! Planner Time: Metareasoning for Probabilistic Planning Using Learned Performance Profiles}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29983},
}

@inproceedings{aaai2025_deterministic_8711,
  title = {{Deterministic Policy Gradient Primal-Dual Methods for Continuous-Space Constrained MDPs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34225},
}

@inproceedings{neurips2024_contextual_72506,
  title = {{Contextual Bilevel Reinforcement Learning for Incentive Alignment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94858},
}

@inproceedings{neurips2024_exploiting_73701,
  title = {{Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93796},
}

@inproceedings{aaai2024_relative_7103,
  title = {{Relative Policy-Transition Optimization for Fast Policy Transfer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29550},
}

@inproceedings{aaai2024_sketched_7352,
  title = {{Sketched Newton Value Iteration for Large-Scale Markov Decision Processes}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29301},
}

@inproceedings{aaai2025_formally_9222,
  title = {{Formally Verified Approximate Policy Iteration}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34868},
}

@inproceedings{aaai2025_semi_10732,
  title = {{Semi-Markovian Planning to Coordinate Aerial and Maritime Medical Evacuation Platforms}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35138},
}

@inproceedings{iclr2024_tree_34437,
  title = {{Tree Search-Based Policy Optimization under Stochastic Execution Delay}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18638},
}

@inproceedings{icml2024_model_45746,
  title = {{Model-based Reinforcement Learning for Parameterized Action Spaces}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32706},
}

@inproceedings{neurips2025_skill_78631,
  title = {{Skill-Driven Neurosymbolic State Abstractions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=ggP2r9S9wY},
}

@inproceedings{neurips2025_faster_80068,
  title = {{Faster Fixed-Point Methods for Multichain MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=vrbUfvcNZ6},
}

@inproceedings{iclr2025_actions_82586,
  title = {{Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29211},
}

@inproceedings{aaai2025_aoi_8131,
  title = {{AoI-MDP: An AoI Optimized Markov Decision Process Dedicated in the Underwater Task (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35247},
}

@inproceedings{aaai2025_on_10171,
  title = {{On Shallow Planning Under Partial Observability}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34860},
}

@inproceedings{aaai2025_scalable_10678,
  title = {{Scalable Solutions for Decision-Making Systems Using Explainable Policy Representations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35199},
}

@inproceedings{aaai2025_the_10979,
  title = {{The Indoor-Training Effect: Unexpected Gains from Distribution Shifts in the Transition Function}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33713},
}

@inproceedings{iclr2024_revalued_34053,
  title = {{REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19022},
}