% Key papers for Offline and networked MARL (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{icml2017_stabilising_36403,
  title = {{Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/778},
}

@inproceedings{icml2018_fully_36706,
  title = {{Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2269},
}

@inproceedings{iclr2022_trust_31054,
  title = {{Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6244},
}

@inproceedings{aaai2022_multi_2429,
  title = {{Multi-Agent Incentive Communication via Decentralized Teammate Modeling}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/09466-multi-agent-incentive-communication-via-decentralized-teammate-modeling/},
}

@inproceedings{neurips2019_value_59172,
  title = {{Value Propagation for Decentralized Networked Deep Multi-agent  Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13341},
}

@inproceedings{icml2020_q_38660,
  title = {{Q-value Path Decomposition for Deep Multiagent Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6337},
}

@inproceedings{neurips2020_scalable_60783,
  title = {{Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18367},
}

@inproceedings{neurips2021_believe_63565,
  title = {{Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26146},
}

@inproceedings{neurips2021_taming_61656,
  title = {{Taming Communication and Sample Complexities in Decentralized Policy Evaluation for Cooperative Multi-Agent Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/26527},
}

@inproceedings{neurips2023_offline_67240,
  title = {{Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/72476},
}

@inproceedings{aaai2022_locality_2374,
  title = {{Locality Matters: A Scalable Value Decomposition Approach for Cooperative Multi-Agent Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/09278-locality-matters-a-scalable-value-decomposition-approach-for-cooperative-multi-agent-reinforcement-learning/},
}

@inproceedings{aaai2024_stas_7241,
  title = {{STAS: Spatial-Temporal Return Decomposition for Solving Sparse Rewards Problems in Multi-agent Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29681},
}

@inproceedings{icml2022_maser_40803,
  title = {{MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17579},
}

@inproceedings{neurips2021_multi_62053,
  title = {{Multi-Agent Reinforcement Learning in Stochastic Networked Systems}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://nips.cc/virtual/2021/poster/27812},
}

@inproceedings{neurips2024_madiff_72045,
  title = {{MADiff: Offline Multi-agent Learning with Diffusion Models}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95274},
}

@inproceedings{aaai2023_learning_4034,
  title = {{Learning from Good Trajectories in Offline Multi-Agent Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26379},
}

@inproceedings{aaai2025_offline_10156,
  title = {{Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34099},
}

@inproceedings{iclr2023_more_33443,
  title = {{More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2023},
  url = {https://iclr.cc/virtual/2023/poster/11311},
}

@inproceedings{icml2021_tesseract_40011,
  title = {{Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2021},
  url = {https://icml.cc/virtual/2021/poster/8723},
}

@inproceedings{iclr2022_dealing_31379,
  title = {{Dealing with Non-Stationarity in MARL via Trust-Region Decomposition}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2022},
  url = {https://iclr.cc/virtual/2022/poster/6464},
}

@inproceedings{neurips2024_scalable_73948,
  title = {{Scalable Constrained Policy Optimization for Safe Multi-agent Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93564},
}

@inproceedings{aaai2025_gtde_9294,
  title = {{GTDE: Grouped Training with Decentralized Execution for Multi-agent Actor-Critic}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34021},
}

@inproceedings{neurips2025_bayesian_75066,
  title = {{Bayesian Ego-graph inference for Networked Multi-Agent Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=3qeTs05bRL},
}

@inproceedings{aaai2024_backpropagation_5264,
  title = {{Backpropagation Through Agents}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29277},
}

@inproceedings{aaai2025_cooperative_8540,
  title = {{Cooperative Policy Agreement: Learning Diverse Policy for Offline MARL}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34465},
}

@inproceedings{aaai2025_explanations_9055,
  title = {{Explanations for Multi-Agent Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/35200},
}

@inproceedings{iclr2024_learning_33771,
  title = {{Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19304},
}

@inproceedings{icml2024_rm_45782,
  title = {{\$rm E(3)\$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/32670},
}

@inproceedings{icml2025_o_46691,
  title = {{O-MAPL: Offline Multi-agent Preference Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45881},
}

@inproceedings{icml2026_value_49653,
  title = {{Value Aggregation with Uncertainty in Online Decentralized MARL}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=4QpCJukdjq},
}

@inproceedings{icml2026_hypole_50656,
  title = {{HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=EVoPYB6ss3},
}

@inproceedings{icml2026_offline_51809,
  title = {{Offline Multi-Agent Reinforcement Learning via Sequential Score Decomposition}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=Q6Kt8mROxg},
}

@inproceedings{icml2026_learning_53930,
  title = {{Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=k9OuSat5IR},
}

@inproceedings{icml2026_diffusing_54851,
  title = {{Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=tHY0G4PhCR},
}

@inproceedings{neurips2024_rgmdt_73758,
  title = {{RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/93745},
}

@inproceedings{neurips2025_mean_75832,
  title = {{Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=CTsdZ3j6dR},
}

@inproceedings{neurips2025_continuous_76049,
  title = {{Continuous Soft Actor-Critic: An Off-Policy Learning Method Robust to Time Discretization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=Ey0mro4vJ6},
}