% Key papers for Off-policy actor-critic with expressive policies (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2018_soft_36989,
  title = {{Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/1986},
}

@inproceedings{icml2018_addressing_36499,
  title = {{Addressing Function Approximation Error in Actor-Critic Methods}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2227},
}

@inproceedings{icml2016_asynchronous_35744,
  title = {{Asynchronous Methods for Deep Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/mniha16.html},
}

@inproceedings{icml2017_reinforcement_36365,
  title = {{Reinforcement Learning with Deep Energy-Based Policies}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/838},
}

@inproceedings{neurips2019_stabilizing_59011,
  title = {{Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14153},
}

@inproceedings{icml2016_continuous_35772,
  title = {{Continuous Deep Q-Learning with Model-based Acceleration}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/gu16.html},
}

@inproceedings{neurips2017_bridging_56187,
  title = {{Bridging the Gap Between Value and Policy Based Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9063},
}

@inproceedings{neurips2018_deep_57012,
  title = {{Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11467},
}

@inproceedings{iclr2021_image_30149,
  title = {{Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3188},
}

@inproceedings{icml2017_improving_36229,
  title = {{Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/733},
}

@inproceedings{iclr2017_combining_28209,
  title = {{Combining policy gradient and Q-learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=B1kJ6H9ex},
}

@inproceedings{aaai2020_discretizing_102197,
  title = {{Discretizing Continuous Action Space for On-Policy Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6059},
}

@inproceedings{iclr2022_mastering_31427,
  title = {{Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6275},
}

@inproceedings{neurips2020_softmax_60848,
  title = {{Softmax Deep Double Deterministic Policy Gradients}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16898},
}

@inproceedings{icml2021_sunrise_39912,
  title = {{SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/10641},
}

@inproceedings{neurips2019_virel_59170,
  title = {{VIREL: A Variational Inference Framework for Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14550},
}

@inproceedings{aaai2021_theoretically_1508,
  title = {{Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/09558-theoretically-principled-deep-rl-acceleration-via-nearest-neighbor-function-approximation/},
}

@inproceedings{aaai2022_sample_2695,
  title = {{Sample-Efficient Reinforcement Learning via Conservative Model-Based Actor-Critic}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/08612-sample-efficient-reinforcement-learning-via-conservative-model-based-actor-critic/},
}

@inproceedings{neurips2019_distributional_58158,
  title = {{Distributional Policy Optimization: An Alternative Approach for Continuous Control}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13354},
}

@inproceedings{aaai2018_alternating_102420,
  title = {{Alternating Optimisation and Quadrature for Robust Control}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11687},
}

@inproceedings{icml2024_seizing_43647,
  title = {{Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34805},
}

@inproceedings{aaai2024_double_5747,
  title = {{Double Buffers CEM-TD3: More Efficient Evolution and Richer Exploration}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29665},
}

@inproceedings{iclr2024_s_35371,
  title = {{S\$2\$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17702},
}

@inproceedings{icml2024_ace_43321,
  title = {{ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35131},
}

@inproceedings{neurips2024_dual_71380,
  title = {{Dual Critic Reinforcement Learning under Partial Observability}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95869},
}

@inproceedings{icml2024_adaptive_43337,
  title = {{Adaptive Horizon Actor-Critic for Policy Learning in Contact-Rich Differentiable Simulation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35115},
}

@inproceedings{icml2024_ompo_44392,
  title = {{OMPO: A Unified Framework for RL under Policy and Dynamics Shifts}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34060},
}

@inproceedings{icml2024_rvi_45725,
  title = {{RVI-SAC: Average Reward Off-Policy Deep Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32727},
}

@inproceedings{icml2025_off_46030,
  title = {{Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46516},
}

@inproceedings{icml2025_maximum_46529,
  title = {{Maximum Entropy Reinforcement Learning with Diffusion Policy}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/46039},
}

@inproceedings{icml2025_hyperspherical_48375,
  title = {{Hyperspherical Normalization for Scalable Deep Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44241},
}

@inproceedings{icml2026_pac_49771,
  title = {{PAC-Bayesian Reinforcement Learning Trains Generalizable Policies}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=5Zwnr6uSlv},
}

@inproceedings{icml2026_convergence_51128,
  title = {{Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Iww9TICvKj},
}

@inproceedings{icml2026_v_52396,
  title = {{\$V\_0\$: A Generalist Value Model for Any Policy at State Zero}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=VYTU8l8WO9},
}

@inproceedings{icml2026_debiased_52825,
  title = {{Debiased Model-based Representations for Sample-efficient Continuous Control}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=ZP1p8k106p},
}

@inproceedings{icml2026_mirror_54409,
  title = {{Mirror Descent Actor Critic via Bounded Advantage Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=ofwEMwiaLU},
}

@inproceedings{icml2026_rn_54780,
  title = {{RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=saZwSnt3r9},
}

@inproceedings{neurips2024_maximum_73685,
  title = {{Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93807},
}

@inproceedings{neurips2025_succeed_75156,
  title = {{Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=4t8dYmu5vG},
}

@inproceedings{neurips2025_actor_76931,
  title = {{Actor-Free Continuous Control via Structurally Maximizable Q-Functions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=OgLRVB78nM},
}