% Key papers for Variance-reduced policy gradients (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{iclr2018_distributed_28642,
  title = {{Distributed Distributional Deterministic Policy Gradients}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/25},
}

@inproceedings{iclr2018_variance_28501,
  title = {{Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/115},
}

@inproceedings{neurips2019_neural_58674,
  title = {{Neural Trust Region/Proximal Policy Optimization Attains Globally Optimal Policy}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14065},
}

@inproceedings{icml2018_structured_37018,
  title = {{Structured Evolution with Compact Architectures for Scalable Policy Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/1907},
}

@inproceedings{neurips2020_variational_61079,
  title = {{Variational Policy Gradient Method for Reinforcement Learning with General Utilities}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17942},
}

@inproceedings{icml2019_taming_37780,
  title = {{Taming MAML: Efficient unbiased meta-reinforcement learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4182},
}

@inproceedings{iclr2020_sample_29475,
  title = {{Sample Efficient Policy Gradient Methods with Recursive Variance Reduction}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=HJlxIJBFDr},
}

@inproceedings{aaai2018_expected_102340,
  title = {{Expected Policy Gradients}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11607},
}

@inproceedings{iclr2018_action_28497,
  title = {{Action-dependent Control Variates for Policy Optimization via Stein Identity}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/106},
}

@inproceedings{icml2019_hessian_37419,
  title = {{Hessian Aided Policy Gradient}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4137},
}

@inproceedings{aaai2021_task_1468,
  title = {{Task-Agnostic Exploration via Policy Gradient of a Non-Parametric State Entropy Estimate}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/09028-task-agnostic-exploration-via-policy-gradient-of-a-non-parametric-state-entropy-estimate/},
}

@inproceedings{neurips2017_cold_56196,
  title = {{Cold-Start Reinforcement Learning with Softmax Policy Gradient}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9067},
}

@inproceedings{neurips2020_independent_60078,
  title = {{Independent Policy Gradient Methods for Competitive Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18456},
}

@inproceedings{neurips2021_on_62227,
  title = {{On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/28616},
}

@inproceedings{neurips2020_robust_60744,
  title = {{Robust Reinforcement Learning via Adversarial training with Langevin Dynamics}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18548},
}

@inproceedings{neurips2020_differentiable_59697,
  title = {{Differentiable Meta-Learning of Bandit Policies}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18464},
}

@inproceedings{aaai2020_gradient_101931,
  title = {{Gradient-Aware Model-Based Policy Search}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5791},
}

@inproceedings{aaai2020_on_102141,
  title = {{On the Role of Weight Sharing During Deep Option Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/6003},
}

@inproceedings{icml2022_policy_41018,
  title = {{Policy Gradient Method For Robust Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16373},
}

@inproceedings{neurips2021_stabilizing_63590,
  title = {{Stabilizing Dynamical Systems via Policy Gradient Methods}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27857},
}

@inproceedings{aaai2024_optimistic_6872,
  title = {{Optimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence beyond the Minty Property}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28799},
}

@inproceedings{aaai2024_generalizable_6112,
  title = {{Generalizable Policy Improvement via Reinforcement Sampling (Student Abstract)}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30466},
}

@inproceedings{icml2024_towards_43788,
  title = {{Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34664},
}

@inproceedings{icml2024_on_44408,
  title = {{On the Second-Order Convergence of Biased Policy Gradient Algorithms}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34044},
}

@inproceedings{icml2025_improving_47106,
  title = {{Improving Value Estimation Critically Enhances Vanilla Policy Gradient}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45480},
}

@inproceedings{icml2025_policy_49110,
  title = {{Policy Gradient with Tree Expansion}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43515},
}

@inproceedings{icml2026_boosting_49626,
  title = {{Boosting CVaR Policy Optimization with Quantile Gradients}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=4De8M6HSF5},
}

@inproceedings{icml2026_emergence_51584,
  title = {{Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=NpvBAOc87E},
}

@inproceedings{icml2026_non_51679,
  title = {{Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Ol99zoW31J},
}

@inproceedings{neurips2024_occupancy_71895,
  title = {{Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95408},
}

@inproceedings{neurips2024_solving_74460,
  title = {{Solving Zero-Sum Markov Games with Continuous State via Spectral Dynamic Embedding}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93114},
}

@inproceedings{neurips2025_pass_77656,
  title = {{Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=W6WC6047X2},
}

@inproceedings{neurips2025_globally_80134,
  title = {{Globally Optimal Policy Gradient Algorithms for Reinforcement Learning with PID Control Policies}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=wW2qRfhT9d},
}

@inproceedings{iclr2026_distributional_84790,
  title = {{Distributional value gradients for stochastic environments}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=6hZAo6fZvJ},
}

@inproceedings{iclr2026_does_86587,
  title = {{Does “Do Differentiable Simulators Give Better Policy Gradients?” Give Better Policy Gradients?}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=RUzxUqTpzW},
}

@inproceedings{iclr2026_asynchronous_86682,
  title = {{Asynchronous Policy Gradient Aggregation for Efficient Distributed Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=SitVEPYv6W},
}

@inproceedings{neurips2026_policy_90105,
  title = {{Policy Gradient Algorithms in Average-Reward Multichain MDPs}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/154239},
}

@inproceedings{neurips2026_delightful_90335,
  title = {{Delightful Distributed Policy Gradient}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/155678},
}

@inproceedings{neurips2026_stabilizing_90490,
  title = {{Stabilizing Policy Optimization via Logits Convexity}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/148304},
}

@inproceedings{neurips2026_breaking_94258,
  title = {{Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/154531},
}