% Key papers for Model-based RL with guarantees (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2016_guided_35860,
  title = {{Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/finn16.html},
}

@inproceedings{iclr2018_model_28598,
  title = {{Model-Ensemble Trust-Region Policy Optimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/111},
}

@inproceedings{iclr2018_maximum_28574,
  title = {{Maximum a Posteriori Policy Optimisation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/9},
}

@inproceedings{iclr2017_learning_28383,
  title = {{Learning to Optimize}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=ry4Vrt5gl},
}

@inproceedings{neurips2018_simple_57625,
  title = {{Simple random search of static linear policies is competitive for reinforcement learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11193},
}

@inproceedings{neurips2018_sample_57598,
  title = {{Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11787},
}

@inproceedings{iclr2019_algorithmic_28760,
  title = {{Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/887},
}

@inproceedings{aaai2016_increasing_105131,
  title = {{Increasing the Action Gap: New Operators for Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10303},
}

@inproceedings{neurips2019_when_59199,
  title = {{When to Trust Your Model: Model-Based Policy Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14205},
}

@inproceedings{neurips2019_a_57808,
  title = {{A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14377},
}

@inproceedings{neurips2019_when_59200,
  title = {{When to use parametric models in reinforcement learning?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14354},
}

@inproceedings{aaai2020_adaptive_102159,
  title = {{Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6021},
}

@inproceedings{neurips2016_safe_55977,
  title = {{Safe and Efficient Off-Policy Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7011},
}

@inproceedings{icml2017_combining_36100,
  title = {{Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/853},
}

@inproceedings{icml2019_action_37122,
  title = {{Action Robust Reinforcement Learning and Applications in Continuous Control}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3585},
}

@inproceedings{neurips2016_guided_55764,
  title = {{Guided Policy Search via Approximate Mirror Descent}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7385},
}

@inproceedings{iclr2019_plan_28828,
  title = {{Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/907},
}

@inproceedings{aaai2019_off_101554,
  title = {{Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4246},
}

@inproceedings{icml2020_a_37870,
  title = {{A Game Theoretic Framework for Model Based Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6314},
}

@inproceedings{iclr2020_robust_29454,
  title = {{Robust Reinforcement Learning for Continuous Control with Model Misspecification}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=HJgC60EtwB},
}

@inproceedings{iclr2024_td_34353,
  title = {{TD-MPC2: Scalable, Robust World Models for Continuous Control}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18722},
}

@inproceedings{aaai2024_risk_7163,
  title = {{Risk-Conditioned Reinforcement Learning: A Generalized Approach for Adapting to Varying Risk Measures}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29589},
}

@inproceedings{aaai2024_pa2d_6885,
  title = {{PA2D-MORL: Pareto Ascent Directional Decomposition Based Multi-Objective Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29148},
}

@inproceedings{aaai2024_reward_7156,
  title = {{Reward Certification for Policy Smoothed Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30139},
}

@inproceedings{aaai2026_chdp_107185,
  title = {{CHDP: Cooperative Hybrid Diffusion Policies for Reinforcement Learning in Parameterized Action Space}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39537},
}

@inproceedings{icml2024_bayesian_44296,
  title = {{Bayesian Exploration Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34156},
}

@inproceedings{icml2024_the_44863,
  title = {{The Max-Min Formulation of Multi-Objective Reinforcement Learning: From Theory to a Model-Free Algorithm}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33589},
}

@inproceedings{icml2026_minimax_50849,
  title = {{MiniMax Learning of Interpretable Factored Stochastic Policies from Conjoint Data, with Uncertainty Quantification}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=GJblFvJcMb},
}

@inproceedings{neurips2025_flow_75804,
  title = {{Flow-Based Policy for Online Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=CANUXhPoyn},
}

@inproceedings{iclr2025_diffusion_83339,
  title = {{Diffusion Policy Policy Optimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28475},
}

@inproceedings{iclr2025_monte_83593,
  title = {{Monte Carlo Planning with Large Language Model for Text-Based Game Agents}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28224},
}

@inproceedings{aaai2025_on_10164,
  title = {{On Corruption-Robustness in Performative Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34196},
}

@inproceedings{iclr2024_robust_34052,
  title = {{Robust Model Based Reinforcement Learning Using \$mathcalL\_1\$ Adaptive Control}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19023},
}

@inproceedings{iclr2024_maximum_35097,
  title = {{Maximum Entropy Model Correction in Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17976},
}

@inproceedings{iclr2024_provably_35540,
  title = {{Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17533},
}

@inproceedings{iclr2024_game_35584,
  title = {{Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17489},
}

@inproceedings{iclr2024_impact_35618,
  title = {{Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17455},
}

@inproceedings{icml2024_learning_43509,
  title = {{Learning to Stabilize Online Reinforcement Learning in Unbounded State Spaces}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34943},
}

@inproceedings{icml2024_switching_43567,
  title = {{Switching the Loss Reduces the Cost in Batch Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34885},
}

@inproceedings{icml2024_reflective_43796,
  title = {{Reflective Policy Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34656},
}