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

@inproceedings{icml2018_global_36717,
  title = {{Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2091},
}

@inproceedings{iclr2017_q_28307,
  title = {{Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2017},
  url = {https://openreview.net/forum?id=SJ3rcZcxl},
}

@inproceedings{iclr2020_implementation_29746,
  title = {{Implementation Matters in Deep RL: A Case Study on PPO and TRPO}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=r1etN1rtPB},
}

@inproceedings{neurips2018_memory_57366,
  title = {{Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11948},
}

@inproceedings{iclr2020_v_29723,
  title = {{V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=SylOlp4FvH},
}

@inproceedings{icml2021_phasic_39784,
  title = {{Phasic Policy Gradient}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8475},
}

@inproceedings{icml2019_understanding_37834,
  title = {{Understanding the Impact of Entropy on Policy Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4104},
}

@inproceedings{icml2018_the_37039,
  title = {{The Mirage of Action-Dependent Baselines in Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2355},
}

@inproceedings{icml2018_learning_36813,
  title = {{Learning to Explore via Meta-Policy Gradient}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/1939},
}

@inproceedings{iclr2020_a_29912,
  title = {{A Closer Look at Deep Policy Gradients}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=ryxdEkHtPS},
}

@inproceedings{aaai2017_offer_104433,
  title = {{OFFER: Off-Environment Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10810},
}

@inproceedings{icml2018_clipped_36572,
  title = {{Clipped Action Policy Gradient}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2018},
}

@inproceedings{icml2018_policy_36923,
  title = {{Policy Optimization as Wasserstein Gradient Flows}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2121},
}

@inproceedings{neurips2019_fast_58259,
  title = {{Fast Efficient Hyperparameter Tuning for Policy Gradient Methods}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13612},
}

@inproceedings{aaai2023_the_4810,
  title = {{The Sufficiency of Off-Policyness and Soft Clipping: PPO Is Still Insufficient according to an Off-Policy Measure}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/25864},
}

@inproceedings{aaai2021_sample_1323,
  title = {{Sample Complexity of Policy Gradient Finding Second-Order Stationary Points}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/10630-sample-complexity-of-policy-gradient-finding-second-order-stationary-points/},
}

@inproceedings{neurips2020_lifelong_60248,
  title = {{Lifelong Policy Gradient Learning of Factored Policies for Faster Training Without Forgetting}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16983},
}

@inproceedings{neurips2017_interpolated_56392,
  title = {{Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9166},
}

@inproceedings{neurips2020_an_59381,
  title = {{An operator view of policy gradient methods}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17917},
}

@inproceedings{aaai2017_policy_104534,
  title = {{Policy Search with High-Dimensional Context Variables}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10911},
}

@inproceedings{iclr2024_identifying_35008,
  title = {{Identifying Policy Gradient Subspaces}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/18066},
}

@inproceedings{icml2024_stabilizing_45803,
  title = {{Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32649},
}

@inproceedings{neurips2024_deep_71138,
  title = {{Deep Policy Gradient Methods Without Batch Updates, Target Networks, or Replay Buffers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96084},
}

@inproceedings{icml2024_sapg_43440,
  title = {{SAPG: Split and Aggregate Policy Gradients}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35012},
}

@inproceedings{icml2024_learning_43671,
  title = {{Learning Optimal Deterministic Policies with Stochastic Policy Gradients}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34781},
}

@inproceedings{icml2024_mollification_43811,
  title = {{Mollification Effects of Policy Gradient Methods}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34641},
}

@inproceedings{icml2024_do_44520,
  title = {{Do Transformer World Models Give Better Policy Gradients?}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33932},
}

@inproceedings{icml2025_convergence_47625,
  title = {{Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44972},
}

@inproceedings{icml2025_return_48030,
  title = {{Return Capping: Sample Efficient CVaR Policy Gradient Optimisation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44577},
}

@inproceedings{icml2026_reparameterization_52211,
  title = {{Reparameterization Proximal Policy Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=TknqRTyQ0a},
}

@inproceedings{icml2026_recurrent_52411,
  title = {{Recurrent Structural Policy Gradient for Partially Observable Mean Field Games}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=VkZQThGNgI},
}

@inproceedings{icml2026_reparameterization_52536,
  title = {{Reparameterization Flow Policy Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Wx5XHJoeyn},
}

@inproceedings{icml2026_spar_52632,
  title = {{SPAR: Support-Preserving Action Rectification}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=XiaqvkSnWk},
}

@inproceedings{icml2026_reusing_53563,
  title = {{Reusing Trajectories in Policy Gradients Enables Fast Convergence}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=gcYvvxTLRA},
}

@inproceedings{neurips2025_on_78074,
  title = {{On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=aq9Nc5NvNc},
}

@inproceedings{iclr2026_relative_84639,
  title = {{Relative Entropy Pathwise Policy Optimization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=4vmm8mlHkS},
}

@inproceedings{iclr2026_sampling_84718,
  title = {{Sampling Complexity of TD and PPO in RKHS}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=5gUMhTUDi0},
}

@inproceedings{iclr2026_policy_86418,
  title = {{Policy Newton Algorithm in Reproducing Kernel Hilbert Space}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=PYnLd91wZY},
}

@inproceedings{iclr2026_rethinking_87869,
  title = {{Rethinking Policy Diversity in Ensemble Policy Gradient in Large-Scale Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=gRdEcs0qdd},
}

@inproceedings{neurips2026_does_90334,
  title = {{Does This Gradient Spark Joy?}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/149741},
}