% Key papers for Policy gradients for special settings (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2019_large_101513,
  title = {{Large-Scale Interactive Recommendation with Tree-Structured Policy Gradient}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/4204},
}

@inproceedings{neurips2020_gradient_59959,
  title = {{Gradient Surgery for Multi-Task Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/16967},
}

@inproceedings{iclr2019_variance_28972,
  title = {{Variance Reduction for Reinforcement Learning in Input-Driven Environments}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/1025},
}

@inproceedings{neurips2018_credit_56987,
  title = {{Credit Assignment For Collective Multiagent RL With Global Rewards}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11776},
}

@inproceedings{neurips2018_learning_57298,
  title = {{Learning Temporal Point Processes via Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/12019},
}

@inproceedings{aaai2021_queue_1221,
  title = {{Queue-Learning: A Reinforcement Learning Approach for Providing Quality of Service}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/00461-queue-learning-a-reinforcement-learning-approach-for-providing-quality-of-service/},
}

@inproceedings{aaai2017_scalable_104565,
  title = {{Scalable Multitask Policy Gradient Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10942},
}

@inproceedings{neurips2021_local_62995,
  title = {{Local policy search with Bayesian optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27748},
}

@inproceedings{icml2019_remember_37695,
  title = {{Remember and Forget for Experience Replay}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4287},
}

@inproceedings{neurips2019_imitation_58391,
  title = {{Imitation-Projected Programmatic Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14462},
}

@inproceedings{iclr2019_marginal_28943,
  title = {{Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/947},
}

@inproceedings{icml2020_batch_37961,
  title = {{Batch Reinforcement Learning with Hyperparameter Gradients}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6388},
}

@inproceedings{neurips2023_policy_69632,
  title = {{Policy Optimization for Continuous Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/70304},
}

@inproceedings{iclr2020_population_29775,
  title = {{Population-Guided Parallel Policy Search for Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=rJeINp4KwH},
}

@inproceedings{icml2018_reinforcement_36956,
  title = {{Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2182},
}

@inproceedings{neurips2024_excluding_74573,
  title = {{Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93013},
}

@inproceedings{neurips2024_adam_72943,
  title = {{Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94469},
}

@inproceedings{neurips2024_learning_74359,
  title = {{Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93202},
}

@inproceedings{neurips2022_continuous_64214,
  title = {{Continuous MDP Homomorphisms and Homomorphic Policy Gradient}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/53319},
}

@inproceedings{iclr2024_time_33660,
  title = {{Time-Efficient Reinforcement Learning with Stochastic Stateful Policies}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19415},
}

@inproceedings{icml2024_global_43247,
  title = {{Global Reinforcement Learning : Beyond Linear and Convex Rewards via Submodular Semi-gradient Methods}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35205},
}

@inproceedings{icml2025_reinforcement_47941,
  title = {{Reinforcement Learning with Random Time Horizons}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44663},
}

@inproceedings{icml2026_rethinking_49569,
  title = {{Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=3mJ9eTU319},
}

@inproceedings{icml2026_sample_49696,
  title = {{Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=4qLPtABOIR},
}

@inproceedings{icml2026_performative_50182,
  title = {{Performative Policy Gradient: Optimality in Performative Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=9qbzrMIw63},
}

@inproceedings{icml2026_dream_52756,
  title = {{Dream-MPC: Gradient-Based Model Predictive Control with Latent Imagination}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Ym6ud8Psx1},
}

@inproceedings{icml2026_from_53748,
  title = {{From Outcomes to Actions: Leveraging Hindsight for Long-Horizon Language Agent Training}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=iK3yDEvQ4y},
}

@inproceedings{icml2026_prorl_54095,
  title = {{ProRL: Effective Reinforcement Learning for Proactive Recommendation via Rectified Policy Gradient Estimation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=loXCDLDwXu},
}

@inproceedings{neurips2024_robust_70756,
  title = {{Robust Reinforcement Learning with General Utility}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96370},
}

@inproceedings{neurips2025_learning_78105,
  title = {{Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=b4pEeU44AB},
}

@inproceedings{iclr2025_pwm_83038,
  title = {{PWM: Policy Learning with Multi-Task World Models}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28766},
}

@inproceedings{iclr2025_learning_83386,
  title = {{Learning mirror maps in policy mirror descent}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/28430},
}

@inproceedings{iclr2026_distributions_84625,
  title = {{Distributions as Actions: A Unified Framework for Diverse Action Spaces}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=4ol71wMPY8},
}

@inproceedings{iclr2026_from_86765,
  title = {{From Ticks to Flows: Dynamics of Neural Reinforcement Learning in Continuous Environments}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=TdiRLe3rPA},
}

@inproceedings{neurips2026_reward_94205,
  title = {{Reward Inflation: A Healthy Stimulus for Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2026},
  url = {https://neurips.cc/virtual/2026/poster/149798},
}

@inproceedings{aaai2026_lppg_107337,
  title = {{LPPG-RL: Lexicographically Projected Policy Gradient Reinforcement Learning with Subproblem Exploration}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39689},
}