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

@inproceedings{aaai2017_the_104539,
  title = {{The Option-Critic Architecture}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10916},
}

@inproceedings{neurips2017_scalable_56656,
  title = {{Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9303},
}

@inproceedings{iclr2017_an_28309,
  title = {{An Actor-Critic Algorithm for Sequence Prediction}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=SJDaqqveg},
}

@inproceedings{iclr2017_sample_28286,
  title = {{Sample Efficient Actor-Critic with Experience Replay}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=HyM25Mqel},
}

@inproceedings{neurips2019_learning_58532,
  title = {{Learning to Perform Local Rewriting for Combinatorial Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13742},
}

@inproceedings{icml2018_self_36980,
  title = {{Self-Imitation Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2101},
}

@inproceedings{neurips2018_actor_56833,
  title = {{Actor-Critic Policy Optimization in Partially Observable Multiagent Environments}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11344},
}

@inproceedings{neurips2019_provably_58851,
  title = {{Provably Global Convergence of Actor-Critic: A Case for Linear Quadratic Regulator with Ergodic Cost}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13899},
}

@inproceedings{iclr2020_model_29695,
  title = {{Model-Augmented Actor-Critic: Backpropagating through Paths}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=Skln2A4YDB},
}

@inproceedings{aaai2022_stackelberg_2776,
  title = {{Stackelberg Actor-Critic: Game-Theoretic Reinforcement Learning Algorithms}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/09217-stackelberg-actor-critic-game-theoretic-reinforcement-learning-algorithms/},
}

@inproceedings{neurips2020_a_59268,
  title = {{A Self-Tuning Actor-Critic Algorithm}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17681},
}

@inproceedings{neurips2019_dac_58075,
  title = {{DAC: The Double Actor-Critic Architecture for Learning Options}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13405},
}

@inproceedings{neurips2020_a_59246,
  title = {{A Finite-Time Analysis of Two Time-Scale Actor-Critic Methods}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17944},
}

@inproceedings{neurips2020_improving_60070,
  title = {{Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17382},
}

@inproceedings{neurips2019_better_57946,
  title = {{Better Exploration with Optimistic Actor Critic}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14497},
}

@inproceedings{iclr2017_reinforcement_28346,
  title = {{Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=r1VGvBcxl},
}

@inproceedings{iclr2018_the_28687,
  title = {{The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/133},
}

@inproceedings{neurips2020_online_60517,
  title = {{Online Meta-Critic Learning for Off-Policy Actor-Critic Methods}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17697},
}

@inproceedings{aaai2019_ace_101811,
  title = {{ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4526},
}

@inproceedings{iclr2021_single_30644,
  title = {{Single-Timescale Actor-Critic Provably Finds Globally Optimal Policy}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/2740},
}

@inproceedings{neurips2024_diffusion_73635,
  title = {{Diffusion Actor-Critic with Entropy Regulator}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93857},
}

@inproceedings{aaai2025_ctd4_8368,
  title = {{CTD4 – a Deep Continuous Distributional Actor-Critic Agent with a Kalman Fusion of Multiple Critics}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35391},
}

@inproceedings{icml2024_relu_43409,
  title = {{ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35043},
}

@inproceedings{aaai2025_decoupled_8664,
  title = {{Decoupled Policy Actor-Critic: Bridging Pessimism and Risk Awareness in Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34162},
}

@inproceedings{aaai2025_single_10771,
  title = {{Single-Loop Federated Actor-Critic across Heterogeneous Environments}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34469},
}

@inproceedings{icml2024_non_44677,
  title = {{Non-Asymptotic Analysis for Single-Loop (Natural) Actor-Critic with Compatible Function Approximation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33775},
}

@inproceedings{icml2024_finite_43290,
  title = {{Finite-Time Convergence and Sample Complexity of Actor-Critic Multi-Objective Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35162},
}

@inproceedings{icml2024_quality_44023,
  title = {{Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34429},
}

@inproceedings{icml2025_actor_45929,
  title = {{Actor-Critics Can Achieve Optimal Sample Efficiency}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46616},
}

@inproceedings{icml2025_a_46663,
  title = {{A Theoretical Justification for Asymmetric Actor-Critic Algorithms}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45909},
}

@inproceedings{icml2026_ac_49445,
  title = {{AC-ODM: Actor–Critic Online Data Mixing for Sample-Efficient LLM Pretraining}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=2bKKamEtto},
}

@inproceedings{icml2026_stabilizing_52336,
  title = {{Stabilizing the Q-Gradient Field for Policy Smoothness in Actor-Critic Methods}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=UpA00uD6Ek},
}

@inproceedings{icml2026_beyond_52767,
  title = {{Beyond the Bellman Recursion: A Pontryagin-Guided Framework for Non-Exponential Discounting}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Ys66H59k8m},
}

@inproceedings{icml2026_shap_52995,
  title = {{SHAP-Guided Kernel Actor-Critic for Explainable Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=b0Z5xWy23m},
}

@inproceedings{icml2026_finite_53693,
  title = {{Finite-time Convergence Analysis of Actor-Critic with Evolving Reward}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=hocdjAEAIm},
}

@inproceedings{icml2026_refined_55399,
  title = {{Refined Analysis of Entropy-Regularized Actor-Critic}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=ybMDCeOC2m},
}

@inproceedings{neurips2025_value_79732,
  title = {{Value Improved Actor Critic Algorithms}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=sTR3xGGU6W},
}

@inproceedings{iclr2025_langevin_81459,
  title = {{Langevin Soft Actor-Critic: Efficient Exploration through Uncertainty-Driven Critic Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/30315},
}

@inproceedings{iclr2026_chunking_88838,
  title = {{Chunking the Critic: A Transformer-based Soft Actor-Critic with N-Step Returns}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=rb5eTktqbc},
}

@inproceedings{neurips2026_mirror_92510,
  title = {{Mirror descent actor-critic methods for entropy regularised MDPs in general spaces: stability and convergence}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/151517},
}