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

@inproceedings{aaai2018_multi_102364,
  title = {{Multi-Step Reinforcement Learning: A Unifying Algorithm}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11631},
}

@inproceedings{neurips2017_reliable_56623,
  title = {{Reliable Decision Support using Counterfactual Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/8960},
}

@inproceedings{icml2018_the_37042,
  title = {{The Uncertainty Bellman Equation and Exploration}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/1959},
}

@inproceedings{aaai2017_sequential_104550,
  title = {{Sequential Classification-Based Optimization for Direct Policy Search}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10927},
}

@inproceedings{icml2019_maximum_37534,
  title = {{Maximum Entropy-Regularized Multi-Goal Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3833},
}

@inproceedings{icml2020_monte_38468,
  title = {{Monte-Carlo Tree Search as Regularized Policy Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6380},
}

@inproceedings{iclr2018_dora_28710,
  title = {{DORA The Explorer: Directed Outreaching Reinforcement Action-Selection}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/261},
}

@inproceedings{aaai2021_universal_1588,
  title = {{Universal Trading for Order Execution with Oracle Policy Distillation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/00107-universal-trading-for-order-execution-with-oracle-policy-distillation/},
}

@inproceedings{icml2017_consistent_36109,
  title = {{Consistent On-Line Off-Policy Evaluation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/480},
}

@inproceedings{neurips2019_trust_59122,
  title = {{Trust Region-Guided Proximal Policy Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13296},
}

@inproceedings{aaai2018_dyetc_106142,
  title = {{DyETC: Dynamic Electronic Toll Collection for Traffic Congestion Alleviation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11337},
}

@inproceedings{icml2017_an_36061,
  title = {{An Alternative Softmax Operator for Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/781},
}

@inproceedings{aaai2021_expected_553,
  title = {{Expected Eligibility Traces}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/09997-expected-eligibility-traces/},
}

@inproceedings{icml2017_efficient_36170,
  title = {{Efficient Nonmyopic Active Search}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/553},
}

@inproceedings{aaai2020_options_102009,
  title = {{Options of Interest: Temporal Abstraction with Interest Functions}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5871},
}

@inproceedings{aaai2018_preventing_106146,
  title = {{Preventing Infectious Disease in Dynamic Populations Under Uncertainty}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11341},
}

@inproceedings{neurips2018_efficient_57090,
  title = {{Efficient nonmyopic batch active search}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11129},
}

@inproceedings{aaai2023_off_4268,
  title = {{Off-Policy Proximal Policy Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26099},
}

@inproceedings{aaai2019_how_101535,
  title = {{How to Combine Tree-Search Methods in Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4227},
}

@inproceedings{aaai2018_noisy_101111,
  title = {{Noisy Derivative-Free Optimization With Value Suppression}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11534},
}

@inproceedings{aaai2024_a_5059,
  title = {{A Reinforcement-Learning-Based Multiple-Column Selection Strategy for Column Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28661},
}

@inproceedings{aaai2024_ovd_6807,
  title = {{OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy Environments}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29303},
}

@inproceedings{aaai2024_deep_5645,
  title = {{Deep Reinforcement Learning for Early Diagnosis of Lung Cancer}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30248},
}

@inproceedings{aaai2024_from_6060,
  title = {{From Past to Future: Rethinking Eligibility Traces}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29115},
}

@inproceedings{aaai2024_learning_6448,
  title = {{Learning Diverse Risk Preferences in Population-Based Self-Play}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29188},
}

@inproceedings{aaai2024_maximizing_6614,
  title = {{Maximizing the Success Probability of Policy Allocations in Online Systems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28982},
}

@inproceedings{aaai2024_optimal_6865,
  title = {{Optimal Mechanism in a Dynamic Stochastic Knapsack Environment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28840},
}

@inproceedings{aaai2024_safear_7249,
  title = {{SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29522},
}

@inproceedings{aaai2025_optimizing_10224,
  title = {{Optimizing Vital Sign Monitoring in Resource-Constrained Maternal Care: An RL-Based Restless Bandit Approach}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35149},
}

@inproceedings{aaai2025_truncated_11111,
  title = {{Truncated Gaussian Policy for Debiased Continuous Control}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33988},
}

@inproceedings{neurips2024_spo_72601,
  title = {{SPO: Sequential Monte Carlo Policy Optimisation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94776},
}

@inproceedings{neurips2025_fairdice_74941,
  title = {{FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=2jQJ7aNdT1},
}

@inproceedings{aaai2026_stability_108498,
  title = {{Stability-Aware Reinforcement Learning for Robust Class Integration Test Order Generation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/40850},
}

@inproceedings{iclr2024_order_34572,
  title = {{Order-Preserving GFlowNets}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18502},
}

@inproceedings{icml2024_probabilistic_44727,
  title = {{Probabilistic Constrained Reinforcement Learning with Formal Interpretability}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33725},
}

@inproceedings{icml2024_adapting_45785,
  title = {{Adapting Static Fairness to Sequential Decision-Making: Bias Mitigation Strategies towards Equal Long-term Benefit Rate}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32667},
}

@inproceedings{icml2025_navigating_45892,
  title = {{Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46651},
}

@inproceedings{icml2025_step_46886,
  title = {{Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45693},
}

@inproceedings{icml2025_trust_47064,
  title = {{Trust-Region Twisted Policy Improvement}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45522},
}

@inproceedings{icml2025_simple_47360,
  title = {{Simple Policy Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45232},
}