% Key papers for Regularized scalable deep value learning (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2016_deep_105123,
  title = {{Deep Reinforcement Learning with Double Q-Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10295},
}

@inproceedings{icml2016_dueling_35807,
  title = {{Dueling Network Architectures for Deep Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/wangf16.html},
}

@inproceedings{neurips2016_deep_55666,
  title = {{Deep Exploration via Bootstrapped DQN}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7014},
}

@inproceedings{icml2019_off_37587,
  title = {{Off-Policy Deep Reinforcement Learning without Exploration}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3655},
}

@inproceedings{neurips2017_hybrid_56368,
  title = {{Hybrid Reward Architecture for Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9314},
}

@inproceedings{icml2017_averaged_36076,
  title = {{Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/566},
}

@inproceedings{iclr2018_temporal_28626,
  title = {{Temporal Difference Models: Model-Free Deep RL for Model-Based Control}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/108},
}

@inproceedings{aaai2021_deeptrader_407,
  title = {{DeepTrader: A Deep Reinforcement Learning Approach for Risk-Return Balanced Portfolio Management with Market Conditions Embedding}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/00643-deeptrader-a-deep-reinforcement-learning-approach-for-risk-return-balanced-portfolio-management-with-market-conditions-embedding/},
}

@inproceedings{neurips2017_concrete_56206,
  title = {{Concrete Dropout}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9141},
}

@inproceedings{neurips2018_randomized_57547,
  title = {{Randomized Prior Functions for Deep Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11823},
}

@inproceedings{aaai2018_bbq_105886,
  title = {{BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11946},
}

@inproceedings{icml2020_revisiting_38703,
  title = {{Revisiting Fundamentals of Experience Replay}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6751},
}

@inproceedings{neurips2018_deep_57013,
  title = {{Deep Reinforcement Learning of Marked Temporal Point Processes}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11321},
}

@inproceedings{iclr2017_learning_28357,
  title = {{Learning to Play in a Day: Faster Deep Reinforcement Learning by Optimality Tightening}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=rJ8Je4clg},
}

@inproceedings{aaai2020_attentive_102187,
  title = {{Attentive Experience Replay}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6049},
}

@inproceedings{neurips2020_reinforcement_60693,
  title = {{Reinforcement Learning with Combinatorial Actions: An Application to Vehicle Routing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18073},
}

@inproceedings{iclr2021_robust_30676,
  title = {{Robust Reinforcement Learning on State Observations with Learned Optimal Adversary}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2624},
}

@inproceedings{neurips2020_discor_59709,
  title = {{DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18124},
}

@inproceedings{neurips2021_deep_63408,
  title = {{Deep Reinforcement Learning at the Edge of the Statistical Precipice}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26712},
}

@inproceedings{aaai2018_temporal_104004,
  title = {{Temporal-Difference Learning With Sampling Baseline for Image Captioning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/12263},
}

@inproceedings{neurips2024_diffusion_72390,
  title = {{Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94963},
}

@inproceedings{aaai2024_fractional_6046,
  title = {{Fractional Deep Reinforcement Learning for Age-Minimal Mobile Edge Computing}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29192},
}

@inproceedings{aaai2024_colored_5422,
  title = {{Colored Noise in PPO: Improved Exploration and Performance through Correlated Action Sampling}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29139},
}

@inproceedings{aaai2024_robustness_7184,
  title = {{Robustness Verification of Deep Reinforcement Learning Based Control Systems Using Reward Martingales}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29976},
}

@inproceedings{aaai2024_analyzing_5189,
  title = {{Analyzing Generalization in Policy Networks: A Case Study with the Double-Integrator System}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29623},
}

@inproceedings{neurips2024_no_72569,
  title = {{No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94803},
}

@inproceedings{neurips2024_improving_73000,
  title = {{Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94420},
}

@inproceedings{neurips2025_proxy_77203,
  title = {{Proxy Target: Bridging the Gap Between Discrete Spiking Neural Networks and Continuous Control}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=RRBve5GwjS},
}

@inproceedings{iclr2024_fast_34217,
  title = {{Fast Value Tracking for Deep Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18858},
}

@inproceedings{icml2024_neural_43281,
  title = {{Neural-Kernel Conditional Mean Embeddings}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35171},
}

@inproceedings{neurips2024_regularized_70480,
  title = {{Regularized Q-Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96628},
}

@inproceedings{neurips2024_non_73214,
  title = {{Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94222},
}

@inproceedings{neurips2024_bigger_73260,
  title = {{Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous control}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94179},
}

@inproceedings{neurips2025_compute_75543,
  title = {{Compute-Optimal Scaling for Value-Based Deep RL}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=9GzyCtlngK},
}

@inproceedings{neurips2025_genpo_75760,
  title = {{GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=BmRNz1TpCc},
}

@inproceedings{neurips2025_scaling_76069,
  title = {{Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=F9jumRh9iu},
}

@inproceedings{iclr2025_simplifying_80937,
  title = {{Simplifying Deep Temporal Difference Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30831},
}

@inproceedings{iclr2025_stabilizing_81312,
  title = {{Stabilizing Reinforcement Learning in Differentiable Multiphysics Simulation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30460},
}

@inproceedings{iclr2026_beyond_84778,
  title = {{Beyond Distributions: Geometric Action Control for Continuous Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=6VqCOnTVXa},
}

@inproceedings{neurips2026_art_92114,
  title = {{ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/155895},
}