% Key papers for Scalable RL systems and environments (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2018_rainbow_102529,
  title = {{Rainbow: Combining Improvements in Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11796},
}

@inproceedings{icml2018_impala_36740,
  title = {{IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2174},
}

@inproceedings{icml2018_rllib_36946,
  title = {{RLlib: Abstractions for Distributed Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2116},
}

@inproceedings{icml2020_agent57_37925,
  title = {{Agent57: Outperforming the Atari Human Benchmark}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6392},
}

@inproceedings{cvpr2018_crafting_12931,
  title = {{Crafting a Toolchain for Image Restoration by Deep Reinforcement Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2018},
  url = {https://openaccess.thecvf.com/content_cvpr_2018/html/Yu_Crafting_a_Toolchain_CVPR_2018_paper.html},
}

@inproceedings{neurips2017_imagination_56372,
  title = {{Imagination-Augmented Agents for Deep Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9343},
}

@inproceedings{aaai2019_multi_101572,
  title = {{Multi-Task Deep Reinforcement Learning with PopArt}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4266},
}

@inproceedings{icml2019_quantifying_37675,
  title = {{Quantifying Generalization in Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3742},
}

@inproceedings{neurips2017_distral_56260,
  title = {{Distral: Robust multitask reinforcement learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9227},
}

@inproceedings{icml2019_a_37096,
  title = {{A Deep Reinforcement Learning Perspective on Internet Congestion Control}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4028},
}

@inproceedings{neurips2018_verifiable_57765,
  title = {{Verifiable Reinforcement Learning via Policy Extraction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11258},
}

@inproceedings{neurips2020_pomo_60565,
  title = {{POMO: Policy Optimization with Multiple Optima for Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17319},
}

@inproceedings{icml2017_darla_36125,
  title = {{DARLA: Improving Zero-Shot Transfer in Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/711},
}

@inproceedings{neurips2018_learn_57271,
  title = {{Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11357},
}

@inproceedings{aaai2018_mathdqn_105921,
  title = {{MathDQN: Solving Arithmetic Word Problems via Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11981},
}

@inproceedings{aaai2017_knowledge_105691,
  title = {{Knowledge Transfer for Deep Reinforcement Learning with Hierarchical Experience Replay}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10733},
}

@inproceedings{neurips2018_data_56992,
  title = {{Data center cooling using model-predictive control}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11380},
}

@inproceedings{aaai2019_sdrl_101352,
  title = {{SDRL: Interpretable and Data-Efficient Deep Reinforcement Learning Leveraging Symbolic Planning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4153},
}

@inproceedings{icml2019_generative_37395,
  title = {{Generative Adversarial User Model for Reinforcement Learning Based Recommendation System}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4202},
}

@inproceedings{icml2023_cleanrl_41443,
  title = {{CleanRL: High-quality Single-file Implementations of Deep Reinforcement Learning Algorithms}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/25648},
}

@inproceedings{neurips2024_digirl_70449,
  title = {{DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96658},
}

@inproceedings{aaai2024_cheaper_5397,
  title = {{Cheaper and Faster: Distributed Deep Reinforcement Learning with Serverless Computing}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29592},
}

@inproceedings{aaai2024_a_5073,
  title = {{A Transfer Approach Using Graph Neural Networks in Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29571},
}

@inproceedings{aaai2024_acamda_5086,
  title = {{ACAMDA: Improving Data Efficiency in Reinforcement Learning through Guided Counterfactual Data Augmentation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29442},
}

@inproceedings{neurips2024_a_70435,
  title = {{A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96670},
}

@inproceedings{aaai2024_improve_6281,
  title = {{Improve Robustness of Reinforcement Learning against Observation Perturbations via l∞ Lipschitz Policy Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29360},
}

@inproceedings{neurips2024_puzzles_71009,
  title = {{PUZZLES: A Benchmark for Neural Algorithmic Reasoning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97818},
}

@inproceedings{neurips2024_interpretable_72737,
  title = {{Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94653},
}

@inproceedings{aaai2025_apirl_7981,
  title = {{APIRL: Deep Reinforcement Learning for REST API Fuzzing}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/31995},
}

@inproceedings{icml2024_craftax_45069,
  title = {{Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33383},
}

@inproceedings{iclr2024_jumanji_33888,
  title = {{Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19187},
}

@inproceedings{icml2024_mixtures_44617,
  title = {{Mixtures of Experts Unlock Parameter Scaling for Deep RL}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33835},
}

@inproceedings{icml2025_benchmarking_46657,
  title = {{Benchmarking Quantum Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45915},
}

@inproceedings{iclr2025_deepseek_81583,
  title = {{DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30193},
}

@inproceedings{aaai2024_crystalbox_5534,
  title = {{CrystalBox: Future-Based Explanations for Input-Driven Deep RL Systems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29372},
}

@inproceedings{aaai2025_neurosymbolic_10117,
  title = {{Neurosymbolic Reinforcement Learning: Playing MiniHack with Probabilistic Logic Shields}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35349},
}

@inproceedings{neurips2024_a_71811,
  title = {{A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95486},
}

@inproceedings{neurips2024_odrl_72875,
  title = {{ODRL: A Benchmark for Off-Dynamics Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97619},
}

@inproceedings{neurips2025_navix_79084,
  title = {{NAVIX: Scaling MiniGrid Environments with JAX}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=lPVz01z0DI},
}

@inproceedings{aaai2026_drmd_100002,
  title = {{DRMD: Deep Reinforcement Learning for Malware Detection Under Concept Drift}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/37053},
}