% Key papers for Stabilizing deep actor-critic (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2018_action_102531,
  title = {{Action Branching Architectures for Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11798},
}

@inproceedings{cvpr2019_self_14790,
  title = {{Self-Critical N-Step Training for Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2019},
}

@inproceedings{iclr2021_what_30619,
  title = {{What Matters for On-Policy Deep Actor-Critic Methods? A Large-Scale Study}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2527},
}

@inproceedings{iclr2017_learning_28200,
  title = {{Learning to Repeat: Fine Grained Action Repetition for Deep Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=B1GOWV5eg},
}

@inproceedings{neurips2020_trust_61018,
  title = {{Trust the Model When It Is Confident: Masked Model-based Actor-Critic}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18801},
}

@inproceedings{iclr2022_dropout_31832,
  title = {{Dropout Q-Functions for Doubly Efficient Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6233},
}

@inproceedings{iclr2021_winning_30211,
  title = {{Winning the L2RPN Challenge: Power Grid Management via Semi-Markov Afterstate Actor-Critic}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3003},
}

@inproceedings{neurips2019_a_57844,
  title = {{A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13864},
}

@inproceedings{aaai2022_stochastic_2784,
  title = {{Stochastic Planner-Actor-Critic for Unsupervised Deformable Image Registration}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/01917-stochastic-planner-actor-critic-for-unsupervised-deformable-image-registration/},
}

@inproceedings{aaai2018_learning_102473,
  title = {{Learning With Options That Terminate Off-Policy}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11740},
}

@inproceedings{aaai2021_addressing_90,
  title = {{Addressing Action Oscillations through Learning Policy Inertia}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/07020-addressing-action-oscillations-through-learning-policy-inertia/},
}

@inproceedings{aaai2024_two_7664,
  title = {{Two-Stage Evolutionary Reinforcement Learning for Enhancing Exploration and Exploitation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30079},
}

@inproceedings{aaai2024_metarlec_6635,
  title = {{MetaRLEC: Meta-Reinforcement Learning for Discovery of Brain Effective Connectivity}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28892},
}

@inproceedings{aaai2021_towered_1544,
  title = {{Towered Actor Critic For Handling Multiple Action Types In Reinforcement Learning For Drug Discovery}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/00142-towered-actor-critic-for-handling-multiple-action-types-in-reinforcement-learning-for-drug-discovery/},
}

@inproceedings{neurips2020_r_60654,
  title = {{R-learning in actor-critic model offers a biologically relevant mechanism for sequential decision-making}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18736},
}

@inproceedings{neurips2020_reinforcement_60690,
  title = {{Reinforcement Learning for Control with Multiple Frequencies}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18560},
}

@inproceedings{neurips2022_monte_64393,
  title = {{Monte Carlo Augmented Actor-Critic for Sparse Reward Deep Reinforcement Learning from Suboptimal Demonstrations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53902},
}

@inproceedings{iclr2022_mathrm_30905,
  title = {{\$mathrmSO(2)\$-Equivariant Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6798},
}

@inproceedings{iclr2023_decision_33086,
  title = {{Decision S4: Efficient Sequence-Based RL via State Spaces Layers}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/10709},
}

@inproceedings{icml2021_recomposing_39858,
  title = {{Recomposing the Reinforcement Learning Building Blocks with Hypernetworks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8489},
}

@inproceedings{icml2024_overestimation_43496,
  title = {{Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34956},
}

@inproceedings{icml2025_a_46454,
  title = {{A Model of Place Field Reorganization During Reward Maximization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46112},
}

@inproceedings{aaai2024_actor_5118,
  title = {{Actor Prioritized Experience Replay (Abstract Reprint)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30610},
}

@inproceedings{aaai2024_virtual_7770,
  title = {{Virtual Action Actor-Critic Framework for Exploration (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30495},
}

@inproceedings{icml2024_trust_44236,
  title = {{Trust the Model Where It Trusts Itself - Model-Based Actor-Critic with Uncertainty-Aware Rollout Adaption}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34216},
}

@inproceedings{aaai2025_the_10973,
  title = {{The Distributional Reward Critic Framework for Reinforcement Learning Under Perturbed Rewards}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/33745},
}

@inproceedings{icml2024_coprocessor_45569,
  title = {{Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32883},
}

@inproceedings{aaai2024_integrating_6334,
  title = {{Integrating Neural Pathways for Learning in Deep Reinforcement Learning Models}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30541},
}

@inproceedings{cvpr2025_stabilizing_27740,
  title = {{Stabilizing and Accelerating Autofocus with Expert Trajectory Regularized Deep Reinforcement Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/35124},
}

@inproceedings{icml2024_learning_43369,
  title = {{Learning a Diffusion Model Policy from Rewards via Q-Score Matching}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35083},
}

@inproceedings{icml2025_efficient_46164,
  title = {{Efficient Online Reinforcement Learning for Diffusion Policy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46396},
}

@inproceedings{icml2025_gradual_47800,
  title = {{Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44800},
}

@inproceedings{icml2026_this_53621,
  title = {{This State Looks Like That: Self-Interpretable Reinforcement Learning Agents using Prototype Soft Actor-Critic}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=hBqL2ugd1M},
}

@inproceedings{neurips2024_cale_74375,
  title = {{CALE: Continuous Arcade Learning Environment}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97454},
}

@inproceedings{neurips2025_structured_76179,
  title = {{Structured Reinforcement Learning for Combinatorial Decision-Making}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=GS9o7u5njS},
}

@inproceedings{neurips2025_learning_80003,
  title = {{Learning to Clean: Reinforcement Learning for Noisy Label Correction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=v8InI8hobW},
}

@inproceedings{iclr2026_towards_86208,
  title = {{Towards Bridging the Gap between Large-Scale Pretraining and Efficient Finetuning for Humanoid Control}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=NEOTsyyYH7},
}

@inproceedings{iclr2026_decoupled_87373,
  title = {{Decoupled Q-Chunking}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=aqGNdZQL9l},
}