% Key papers for Alternative policy update rules (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2017_self_12615,
  title = {{Self-Critical Sequence Training for Image Captioning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{neurips2020_disk_59632,
  title = {{DISK: Learning local features with policy gradient}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16979},
}

@inproceedings{neurips2018_evolved_57107,
  title = {{Evolved Policy Gradients}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11527},
}

@inproceedings{iclr2019_cem_28794,
  title = {{CEM-RL: Combining evolutionary and gradient-based methods for policy search}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/1031},
}

@inproceedings{iclr2020_es_29584,
  title = {{ES-MAML: Simple Hessian-Free Meta Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=S1exA2NtDB},
}

@inproceedings{neurips2018_evolution_57105,
  title = {{Evolution-Guided Policy Gradient in Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11137},
}

@inproceedings{icml2018_spotlight_36996,
  title = {{Spotlight: Optimizing Device Placement for Training Deep Neural Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2032},
}

@inproceedings{neurips2020_meta_60302,
  title = {{Meta-Gradient Reinforcement Learning with an Objective Discovered Online}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18175},
}

@inproceedings{icml2018_pipps_36913,
  title = {{PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/1978},
}

@inproceedings{iclr2020_learning_29363,
  title = {{Learning to solve the credit assignment problem}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=ByeUBANtvB},
}

@inproceedings{aaai2019_trust_101638,
  title = {{Trust Region Evolution Strategies}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4345},
}

@inproceedings{iclr2019_learning_28993,
  title = {{Learning Self-Imitating Diverse Policies}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/986},
}

@inproceedings{icml2019_predictor_37663,
  title = {{Predictor-Corrector Policy Optimization}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3970},
}

@inproceedings{iclr2018_policy_28466,
  title = {{Policy Optimization by Genetic Distillation}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/160},
}

@inproceedings{iclr2018_divide_28682,
  title = {{Divide-and-Conquer Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/100},
}

@inproceedings{icml2019_learning_37486,
  title = {{Learning Novel Policies For Tasks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4274},
}

@inproceedings{neurips2022_ttopt_64624,
  title = {{TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54505},
}

@inproceedings{icml2020_asynchronous_37949,
  title = {{Asynchronous Coagent Networks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/5899},
}

@inproceedings{neurips2018_genetic_57172,
  title = {{Genetic-Gated Networks for Deep Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11188},
}

@inproceedings{aaai2022_an_1734,
  title = {{An Efficient Combinatorial Optimization Model Using Learning-to-Rank Distillation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/08666-an-efficient-combinatorial-optimization-model-using-learning-to-rank-distillation/},
}

@inproceedings{neurips2024_difftori_71818,
  title = {{DiffTORI: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95479},
}

@inproceedings{icml2025_gradient_47475,
  title = {{Gradient Boosting Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45118},
}

@inproceedings{neurips2024_adaptive_74319,
  title = {{Adaptive Labeling for Efficient Out-of-distribution Model Evaluation}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93241},
}

@inproceedings{icml2024_gflownet_43938,
  title = {{GFlowNet Training by Policy Gradients}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34514},
}

@inproceedings{icml2025_analytical_48757,
  title = {{Analytical Lyapunov Function Discovery: An RL-based Generative Approach}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/43865},
}

@inproceedings{icml2026_credit_53894,
  title = {{Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=jnguJEJmYP},
}

@inproceedings{icml2026_open_55314,
  title = {{Open Materials Generation with Inference-Time Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=xfHppnGXaH},
}

@inproceedings{neurips2025_stable_77624,
  title = {{Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Vqj65VeDOu},
}

@inproceedings{neurips2025_adaptive_79335,
  title = {{Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=oGmROC4e4W},
}

@inproceedings{iclr2026_entropy_85414,
  title = {{Entropy-preserving reinforcement learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=E8MR8jgEeZ},
}

@inproceedings{neurips2026_signal_91572,
  title = {{Signal-Adaptive Trust Regions for Gradient-Free Optimization of Recurrent Spiking Neural Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/150835},
}

@inproceedings{neurips2026_cost_92321,
  title = {{Cost-Aware Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/151093},
}

@inproceedings{neurips2026_one_92836,
  title = {{One More Time: Revisiting Neural Quantum States from a Reinforcement Learning Perspective}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/154314},
}

@inproceedings{iclr2025_residual_80664,
  title = {{Residual Kernel Policy Network: Enhancing Stability and Robustness in RKHS-Based Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/31103},
}

@inproceedings{iclr2026_efficient_88904,
  title = {{Efficient Morphology–Control Co-Design via Stackelberg PPO under Non-Differentiable Leader–Follower Interfaces}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=sJ0vOOkclw},
}

@inproceedings{neurips2026_instability_95347,
  title = {{Instability of Meta-Learning Intrinsic Rewards for Policy Gradient Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/150789},
}