% Key papers for RL for combinatorial routing (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{cvpr2017_action_12040,
  title = {{Action-Decision Networks for Visual Tracking With Deep Reinforcement Learning}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2017},
}

@inproceedings{aaai2020_toward_101884,
  title = {{Toward A Thousand Lights: Decentralized Deep Reinforcement Learning for Large-Scale Traffic Signal Control}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5744},
}

@inproceedings{neurips2020_learning_60224,
  title = {{Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/18230},
}

@inproceedings{aaai2018_cellular_106144,
  title = {{Cellular Network Traffic Scheduling With Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2018},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11339},
}

@inproceedings{neurips2018_differentiable_57032,
  title = {{Differentiable MPC for End-to-end Planning and Control}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11793},
}

@inproceedings{neurips2017_thinking_56725,
  title = {{Thinking Fast and Slow with Deep Learning and Tree Search}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2017},
  url = {https://nips.cc/virtual/2017/poster/9311},
}

@inproceedings{neurips2018_reinforcement_57562,
  title = {{Reinforcement Learning for Solving the Vehicle Routing Problem}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11934},
}

@inproceedings{iclr2018_nervenet_28589,
  title = {{NerveNet: Learning Structured Policy with Graph Neural Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/66},
}

@inproceedings{aaai2021_online_1108,
  title = {{Online 3D Bin Packing with Constrained Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/00741-online-3d-bin-packing-with-constrained-deep-reinforcement-learning/},
}

@inproceedings{aaai2019_a_100589,
  title = {{A Deep Reinforcement Learning Framework for Rebalancing Dockless Bike Sharing Systems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2019},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/3940},
}

@inproceedings{iclr2018_n2n_28415,
  title = {{N2N learning: Network to Network Compression via Policy Gradient Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2018},
  url = {https://iclr.cc/virtual/2018/poster/132},
}

@inproceedings{aaai2021_multi_1012,
  title = {{Multi-Decoder Attention Model with Embedding Glimpse for Solving Vehicle Routing Problems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/12042-multi-decoder-attention-model-with-embedding-glimpse-for-solving-vehicle-routing-problems/},
}

@inproceedings{iclr2019_model_28974,
  title = {{Model-Predictive Policy Learning with Uncertainty Regularization for Driving in Dense Traffic}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2019},
  url = {https://iclr.cc/virtual/2019/poster/1121},
}

@inproceedings{aaai2016_efficient_105346,
  title = {{Efficient Macroscopic Urban Traffic Models for Reducing Congestion: A PDDL+ Planning Approach}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2016},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10399},
}

@inproceedings{iclr2020_exploring_29406,
  title = {{Exploring Model-based Planning with Policy Networks}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2020},
  url = {https://openreview.net/forum?id=H1exf64KwH},
}

@inproceedings{neurips2016_strategic_56019,
  title = {{Strategic Attentive Writer for Learning Macro-Actions}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/6971},
}

@inproceedings{aaai2017_landmark_106034,
  title = {{Landmark-Based Heuristics for Goal Recognition}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/11021},
}

@inproceedings{cvpr2020_exploring_15507,
  title = {{Exploring Data Aggregation in Policy Learning for Vision-Based Urban Autonomous Driving}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2020},
}

@inproceedings{neurips2016_generating_55751,
  title = {{Generating Long-term Trajectories Using Deep Hierarchical Networks}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/6932},
}

@inproceedings{aaai2021_combining_266,
  title = {{Combining Reinforcement Learning with Lin-Kernighan-Helsgaun Algorithm for the Traveling Salesman Problem}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/12445-combining-reinforcement-learning-with-lin-kernighan-helsgaun-algorithm-for-the-traveling-salesman-problem/},
}

@inproceedings{aaai2024_prompt_7010,
  title = {{Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/27758},
}

@inproceedings{aaai2024_light_7857,
  title = {{π-Light: Programmatic Interpretable Reinforcement Learning for Resource-Limited Traffic Signal Control}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30103},
}

@inproceedings{cvpr2025_carplanner_25683,
  title = {{CarPlanner: Consistent Auto-regressive Trajectory Planning for Large-Scale Reinforcement Learning in Autonomous Driving}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2025},
  url = {https://cvpr.thecvf.com/virtual/2025/poster/34678},
}

@inproceedings{aaai2024_graph_6162,
  title = {{Graph-Based Prediction and Planning Policy Network (GP3Net) for Scalable Self-Driving in Dynamic Environments Using Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29043},
}

@inproceedings{aaai2024_improving_6289,
  title = {{Improving Autonomous Separation Assurance through Distributed Reinforcement Learning with Attention Networks}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/30321},
}

@inproceedings{aaai2024_not_6794,
  title = {{Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29129},
}

@inproceedings{aaai2026_worldrft_105277,
  title = {{WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2026},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/38149},
}

@inproceedings{neurips2024_neuralplane_71697,
  title = {{NeuralPlane: An Efficiently Parallelizable Platform for Fixed-wing Aircraft Control with Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97741},
}

@inproceedings{neurips2025_rad_75564,
  title = {{RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=9V3crVSPH7},
}

@inproceedings{aaai2024_hierarchical_6206,
  title = {{Hierarchical Planning and Learning for Robots in Stochastic Settings Using Zero-Shot Option Invention}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/28903},
}

@inproceedings{aaai2025_garlic_9263,
  title = {{GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/32002},
}

@inproceedings{aaai2025_scaling_10687,
  title = {{Scaling Combinatorial Optimization Neural Improvement Heuristics with Online Search and Adaptation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34921},
}

@inproceedings{neurips2024_qgym_74212,
  title = {{QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/97467},
}

@inproceedings{aaai2025_in_9542,
  title = {{In Search of Trees: Decision-Tree Policy Synthesis for Black-Box Systems via Search}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34934},
}

@inproceedings{cvpr2024_versatile_25206,
  title = {{Versatile Navigation Under Partial Observability via Value-guided Diffusion Policy}},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2024},
  url = {https://cvpr.thecvf.com/virtual/2024/poster/30763},
}

@inproceedings{iclr2024_dynamic_33733,
  title = {{Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/19342},
}

@inproceedings{neurips2025_vlmlight_74687,
  title = {{VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=08mjueZ0Iq},
}

@inproceedings{neurips2025_from_79628,
  title = {{From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=rMQvbxxmLe},
}

@inproceedings{aaai2025_reducing_10490,
  title = {{Reducing AUV Energy Consumption Through Dynamic Sensor Directions Switching via Deep Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34074},
}

@inproceedings{icml2024_invit_43295,
  title = {{INViT: A Generalizable Routing Problem Solver with Invariant Nested View Transformer}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/35157},
}