% Key papers for Task structure and curricula for meta-RL (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{aaai2020_metalight_100294,
  title = {{MetaLight: Value-Based Meta-Reinforcement Learning for Traffic Signal Control}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5467},
}

@inproceedings{iclr2018_meta_28639,
  title = {{META LEARNING SHARED HIERARCHIES}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/149},
}

@inproceedings{icml2017_zero_36460,
  title = {{Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2017},
  url = {https://icml.cc/virtual/2017/poster/822},
}

@inproceedings{iclr2020_varibad_29509,
  title = {{VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=Hkl9JlBYvr},
}

@inproceedings{neurips2022_finrl_64677,
  title = {{FinRL-Meta: Market Environments and Benchmarks for Data-Driven Financial Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/55620},
}

@inproceedings{neurips2019_unsupervised_59152,
  title = {{Unsupervised Curricula for Visual Meta-Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/14589},
}

@inproceedings{iclr2019_learning_29095,
  title = {{Learning a Meta-Solver for Syntax-Guided Program Synthesis}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/801},
}

@inproceedings{icml2023_human_43087,
  title = {{Human-Timescale Adaptation in an Open-Ended Task Space}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2023},
  url = {https://icml.cc/virtual/2023/poster/24626},
}

@inproceedings{icml2022_recurrent_41070,
  title = {{Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/16431},
}

@inproceedings{aaai2024_generalizable_6114,
  title = {{Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29658},
}

@inproceedings{neurips2018_the_57688,
  title = {{The Importance of Sampling inMeta-Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11884},
}

@inproceedings{icml2022_transformers_41291,
  title = {{Transformers are Meta-Reinforcement Learners}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2022},
  url = {https://icml.cc/virtual/2022/poster/17085},
}

@inproceedings{aaai2023_hypernetworks_3856,
  title = {{Hypernetworks for Zero-Shot Transfer in Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26146},
}

@inproceedings{aaai2023_warm_4951,
  title = {{Warm-Starting Nested Rollout Policy Adaptation with Optimal Stopping}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2023},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/26459},
}

@inproceedings{neurips2021_alchemy_62780,
  title = {{Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2021},
  url = {https://openreview.net/forum?id=eZu4BZxlRnX},
}

@inproceedings{iclr2019_learning_28831,
  title = {{Learning to Design RNA}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/921},
}

@inproceedings{neurips2022_meta_65470,
  title = {{Meta-Reinforcement Learning with Self-Modifying Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2022},
  url = {https://nips.cc/virtual/2022/poster/54938},
}

@inproceedings{neurips2023_metabox_69176,
  title = {{MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2023},
  url = {https://nips.cc/virtual/2023/poster/73497},
}

@inproceedings{aaai2025_configx_8498,
  title = {{ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34904},
}

@inproceedings{iclr2021_sample_30538,
  title = {{Sample-Efficient Automated Deep Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2021},
  url = {https://iclr.cc/virtual/2021/poster/3206},
}

@inproceedings{neurips2024_xland_74652,
  title = {{XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97425},
}

@inproceedings{neurips2025_metabox_75076,
  title = {{MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=415T06x0vG},
}

@inproceedings{neurips2025_towards_78107,
  title = {{Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=b6ASJBXtgP},
}

@inproceedings{aaai2026_out_106929,
  title = {{Out-of-Distribution Generalization with a SPARC: Racing 100 Unseen Vehicles with a Single Policy}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39281},
}

@inproceedings{icml2025_task_47598,
  title = {{Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44998},
}

@inproceedings{neurips2024_dynamite_71933,
  title = {{DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95373},
}

@inproceedings{neurips2025_a_76762,
  title = {{A Bayesian Fast-Slow Framework to Mitigate Interference in Non-Stationary Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=MmjW4VGKbh},
}

@inproceedings{aaai2026_mrcom_107581,
  title = {{MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/39933},
}

@inproceedings{icml2024_meta_45243,
  title = {{Meta-Reinforcement Learning Robust to Distributional Shift Via Performing Lifelong In-Context Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33209},
}

@inproceedings{icml2026_structured_49724,
  title = {{Structured Expert Routing with Multi-View Task Priors for Offline Meta-Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=5AUITfUstd},
}

@inproceedings{neurips2025_modelling_75715,
  title = {{Modelling the control of offline processing with reinforcement learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=BFW1fkB8ck},
}

@inproceedings{neurips2025_predictive_80360,
  title = {{Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=ykDUVoelgj},
}

@inproceedings{iclr2025_efficient_82306,
  title = {{Efficient Cross-Episode Meta-RL}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2025},
  url = {https://iclr.cc/virtual/2025/poster/29485},
}

@inproceedings{iclr2026_the_85283,
  title = {{The State of Reinforcement Finetuning for Transformer-based Generative Agents}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2026},
  url = {https://openreview.net/forum?id=Cbg9MR6dR7},
}