% Key papers for Temporal-difference and discounting theory (scime atlas, https://atlas.scime.ai). Authors are not included: add them from the paper pages.

@inproceedings{neurips2018_meta_57370,
  title = {{Meta-Gradient Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11249},
}

@inproceedings{icml2019_information_37452,
  title = {{Information-Theoretic Considerations in Batch Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4162},
}

@inproceedings{neurips2016_learning_55846,
  title = {{Learning values across many orders of magnitude}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2016},
  url = {https://nips.cc/virtual/2016/poster/7311},
}

@inproceedings{icml2016_generalization_35851,
  title = {{Generalization and Exploration via Randomized Value Functions}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2016},
  url = {https://proceedings.mlr.press/v48/osband16.html},
}

@inproceedings{neurips2020_discovering_59711,
  title = {{Discovering Reinforcement Learning Algorithms}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17706},
}

@inproceedings{aaai2017_transfer_104419,
  title = {{Transfer Reinforcement Learning with Shared Dynamics}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10796},
}

@inproceedings{icml2019_dynamic_37319,
  title = {{Dynamic Weights in Multi-Objective Deep Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3636},
}

@inproceedings{aaai2022_efficient_2018,
  title = {{Efficient Continuous Control with Double Actors and Regularized Critics}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2022},
  url = {https://aaai.org/papers/07655-efficient-continuous-control-with-double-actors-and-regularized-critics/},
}

@inproceedings{neurips2019_a_57810,
  title = {{A Geometric Perspective on Optimal Representations for Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13591},
}

@inproceedings{neurips2020_munchausen_60376,
  title = {{Munchausen Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2020},
  url = {https://nips.cc/virtual/2020/poster/17663},
}

@inproceedings{icml2019_revisiting_37700,
  title = {{Revisiting the Softmax Bellman Operator: New Benefits and New Perspective}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/4170},
}

@inproceedings{aaai2021_reinforcement_1256,
  title = {{Reinforcement Learning with a Disentangled Universal Value Function for Item Recommendation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2021},
  url = {https://aaai.org/papers/04427-reinforcement-learning-with-a-disentangled-universal-value-function-for-item-recommendation/},
}

@inproceedings{icml2018_least_36820,
  title = {{Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2018},
  url = {https://icml.cc/virtual/2018/poster/2004},
}

@inproceedings{icml2020_discount_38107,
  title = {{Discount Factor as a Regularizer in Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2020},
  url = {https://icml.cc/virtual/2020/poster/6021},
}

@inproceedings{neurips2019_successor_59041,
  title = {{Successor Uncertainties: Exploration and Uncertainty in Temporal Difference Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2019},
  url = {https://nips.cc/virtual/2019/poster/13604},
}

@inproceedings{icml2019_composing_37238,
  title = {{Composing Value Functions in Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2019},
  url = {https://icml.cc/virtual/2019/poster/3993},
}

@inproceedings{neurips2018_iterative_57254,
  title = {{Iterative Value-Aware Model Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11865},
}

@inproceedings{aaai2020_fixed_101924,
  title = {{Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2020},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/5784},
}

@inproceedings{neurips2018_reinforcement_57564,
  title = {{Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2018},
  url = {https://nips.cc/virtual/2018/poster/11906},
}

@inproceedings{aaai2017_estimating_104510,
  title = {{Estimating the Maximum Expected Value in Continuous Reinforcement Learning Problems}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2017},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/10887},
}

@inproceedings{aaai2024_erl_5783,
  title = {{ERL-TD: Evolutionary Reinforcement Learning Enhanced with Truncated Variance and Distillation Mutation}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29289},
}

@inproceedings{aaai2024_discerning_5702,
  title = {{Discerning Temporal Difference Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29335},
}

@inproceedings{icml2024_stop_44901,
  title = {{Stop Regressing: Training Value Functions via Classification for Scalable Deep RL}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33551},
}

@inproceedings{aaai2024_parameterized_6925,
  title = {{Parameterized Projected Bellman Operator}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29465},
}

@inproceedings{neurips2024_an_71588,
  title = {{An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95682},
}

@inproceedings{neurips2024_the_72074,
  title = {{The surprising efficiency of temporal difference learning for rare event prediction}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95250},
}

@inproceedings{neurips2024_the_72384,
  title = {{The Value of Reward Lookahead in Reinforcement Learning}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/94968},
}

@inproceedings{aaai2024_symmetric_7457,
  title = {{Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2024},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/29362},
}

@inproceedings{icml2025_the_47384,
  title = {{The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/45208},
}

@inproceedings{neurips2024_temporal_70778,
  title = {{Temporal-Difference Learning Using Distributed Error Signals}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/96351},
}

@inproceedings{neurips2024_adaptive_71404,
  title = {{Adaptive Exploration for Data-Efficient General Value Function Evaluations}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2024},
  url = {https://neurips.cc/virtual/2024/poster/95848},
}

@inproceedings{neurips2025_continuous_79313,
  title = {{Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control}},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year = {2025},
  url = {https://openreview.net/forum?id=o8F5lNOTG6},
}

@inproceedings{aaai2025_me_9841,
  title = {{ME: Modelling Ethical Values for Value Alignment}},
  booktitle = {AAAI Conference on Artificial Intelligence (AAAI)},
  year = {2025},
  url = {https://ojs.aaai.org/index.php/AAAI/article/view/34974},
}

@inproceedings{iclr2024_on_35360,
  title = {{On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17713},
}

@inproceedings{iclr2024_starc_35578,
  title = {{STARC: A General Framework For Quantifying Differences Between Reward Functions}},
  booktitle = {International Conference on Learning Representations (ICLR)},
  year = {2024},
  url = {https://iclr.cc/virtual/2024/poster/17495},
}

@inproceedings{icml2024_stochastic_43986,
  title = {{Stochastic Q-learning for Large Discrete Action Spaces}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34466},
}

@inproceedings{icml2024_sequence_44262,
  title = {{Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/34190},
}

@inproceedings{icml2024_learning_45142,
  title = {{Learning the Target Network in Function Space}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2024},
  url = {https://icml.cc/virtual/2024/poster/33310},
}

@inproceedings{icml2025_calibrated_48095,
  title = {{Calibrated Value-Aware Model Learning with Probabilistic Environment Models}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2025},
  url = {https://icml.cc/virtual/2025/poster/44513},
}

@inproceedings{icml2026_rationality_51991,
  title = {{Rationality Measurement and Theory for Reinforcement Learning Agents}},
  booktitle = {International Conference on Machine Learning (ICML)},
  year = {2026},
  url = {https://openreview.net/forum?id=RlEPV6ec7P},
}