@conference{ Corsi2024Verification,
  Title = "Verification-Guided Shielding for Deep Reinforcement Learning",
  Author = "Davide Corsi and Guy Amir and Andoni Rodríguez and César Sánchez and Guy Katz and Roy Fox",
  Booktitle = "1st Reinforcement Learning Conference (RLC)",
  Year = "2024"
}

@conference{ Karamzade2024Delayed,
  Title = "Reinforcement Learning from Delayed Observations via World Models",
  Author = "Armin Karamzade and Kyungmin Kim and Montek Kalsi and Roy Fox",
  Booktitle = "1st Reinforcement Learning Conference (RLC)",
  Year = "2024"
}

@conference{ Nottingham2024SSO,
  Title = "Skill Set Optimization: Reinforcing Language Model Behavior via Transferable Skills",
  Author = "Kolby Nottingham and Bodhisattwa Prasad Majumder and Bhavana Dalvi Mishra and Sameer Singh and Peter Clark and Roy Fox",
  Booktitle = "41st International Conference on Machine Learning (ICML)",
  Year = "2024"
}

@conference{ Nottingham2024BLINDER,
  Title = "Selective Perception: Learning Concise State Descriptions for Language Model Actors",
  Author = "Kolby Nottingham and Yasaman Razeghi and Kyungmin Kim and JB Lanier and Pierre Baldi and Roy Fox and Sameer Singh",
  Booktitle = "2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)",
  Year = "2024"
}

@conference{ McAleer2024SPPSRO,
  Title = "Toward Optimal Policy Population Growth in Two-Player Zero-Sum Games",
  Author = "Stephen McAleer and JB Lanier and Kevin Wang and Pierre Baldi and Tuomas Sandholm and Roy Fox",
  Booktitle = "12th International Conference on Learning Representations (ICLR)",
  Year = "2024"
}

@conference{ Nottingham2023DECKARD,
  Title = "Do Embodied Agents Dream of Pixelated Sheep?: Embodied Decision Making using Language Guided World Modelling",
  Author = "Kolby Nottingham and Prithviraj Ammanabrolu and Alane Suhr and Yejin Choi and Hannaneh Hajishirzi and Sameer Singh and Roy Fox",
  Booktitle = "40th International Conference on Machine Learning (ICML)",
  Year = "2023"
}

@conference{ Liang2022MeanQ,
  Title = "Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks",
  Author = "Litian Liang and Yaosheng Xu and Stephen McAleer and Dailin Hu and Alexander Ihler and Pieter Abbeel and Roy Fox",
  Booktitle = "39th International Conference on Machine Learning (ICML)",
  Year = "2022"
}

@conference{ Nottingham2022Query,
  Title = "Learning to Query Internet Text for Informing Reinforcement Learning Agents",
  Author = "Kolby Nottingham and Alekhya Pyla and Sameer Singh and Roy Fox",
  Booktitle = "Reinforcement Learning and Decision Making (RLDM)",
  Year = "2022"
}

@conference{ Fox2022MPG,
  Title = "Independent Natural Policy Gradient Always Converges in {M}arkov {P}otential {G}ames",
  Author = "Roy Fox and Stephen McAleer and William Overman and Ioannis Panageas",
  Booktitle = "25th International Conference on Artificial Intelligence and Statistics (AISTATS)",
  Year = "2022"
}

@conference{ McAleer2021XDO,
  Title = "{XDO}: A Double Oracle Algorithm for Extensive-Form Games",
  Author = "Stephen McAleer and JB Lanier and Kevin Wang and Pierre Baldi and Roy Fox",
  Booktitle = "35th Conference on Neural Information Processing Systems (NeurIPS)",
  Year = "2021"
}

@conference{ McAleer2020P2SRO,
  Title = "Pipeline {PSRO}: A Scalable Approach for Finding Approximate {N}ash Equilibria in Large Games",
  Author = "Stephen McAleer and JB Lanier and Roy Fox and Pierre Baldi",
  Booktitle = "34th Conference on Neural Information Processing Systems (NeurIPS)",
  Year = "2020"
}

@conference{ Kim2024Segmentation,
  Title = "Make the Pertinent Salient: Task-Relevant Reconstruction for Visual Control with Distraction",
  Author = "Kyungmin Kim and Charless Fowlkes and Roy Fox",
  Booktitle = "Training Agents with Foundation Models workshop (TAFM @ RLC)",
  Year = "2024"
}

@conference{ Agostinelli2024Qstar,
  Title = "{Q}* Search: Heuristic Search with {D}eep {Q}-{N}etworks",
  Author = "Forest Agostinelli and Shahaf Shperberg and Alexander Shmakov and Stephen McAleer and Roy Fox and Pierre Baldi",
  Booktitle = "Bridging the Gap Between AI Planning and Reinforcement Learning workshop (PRL @ ICAPS)",
  Year = "2024"
}

@conference{ Nottingham2023BLINDER,
  Title = "Selective Perception: Learning Concise State Descriptions for Language Model Actors",
  Author = "Kolby Nottingham and Yasaman Razeghi and Kyungmin Kim and JB Lanier and Pierre Baldi and Roy Fox and Sameer Singh",
  Booktitle = "Foundation Models for Decision Making workshop (FMDM @ NeurIPS)",
  Year = "2023"
}

@conference{ Nottingham2023DECKARDws,
  Title = "Do Embodied Agents Dream of Pixelated Sheep?: Embodied Decision Making using Language Guided World Modelling",
  Author = "Kolby Nottingham and Prithviraj Ammanabrolu and Alane Suhr and Yejin Choi and Hannaneh Hajishirzi and Sameer Singh and Roy Fox",
  Booktitle = "Reincarnating Reinforcement Learning workshop (RRL @ ICLR)",
  Year = "2023"
}

@conference{ Lanier2022FARR,
  Title = "Feasible Adversarial Robust Reinforcement Learning for Underspecified Environments",
  Author = "JB Lanier and Stephen McAleer and Pierre Baldi and Roy Fox",
  Booktitle = "Deep Reinforcement Learning workshop (DRL @ NeurIPS)",
  Year = "2022"
}

@conference{ McAleer2022APSRO,
  Title = "Anytime {PSRO} for Two-Player Zero-Sum Games",
  Author = "Stephen McAleer and Kevin Wang and JB Lanier and Marc Lanctot and Pierre Baldi and Tuomas Sandholm and Roy Fox",
  Booktitle = "Reinforcement Learning in Games workshop (RLG @ AAAI)",
  Year = "2022"
}

@conference{ Liang2021UQL,
  Title = "Temporal-Difference Value Estimation via Uncertainty-Guided Soft Updates",
  Author = "Litian Liang and Yaosheng Xu and Stephen McAleer and Dailin Hu and Alexander Ihler and Pieter Abbeel and Roy Fox",
  Booktitle = "Deep Reinforcement Learning workshop (DRL @ NeurIPS)",
  Year = "2021"
}

@conference{ Hu2021CBSQL,
  Title = "Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning",
  Author = "Dailin Hu and Pieter Abbeel and Roy Fox",
  Booktitle = "Deep Reinforcement Learning workshop (DRL @ NeurIPS)",
  Year = "2021"
}

@conference{ Xu2021TESSAC,
  Title = "Target Entropy Annealing for Discrete {S}oft {A}ctor–{C}ritic",
  Author = "Yaosheng Xu and Dailin Hu and Litian Liang and Stephen McAleer and Pieter Abbeel and Roy Fox",
  Booktitle = "Deep Reinforcement Learning workshop (DRL @ NeurIPS)",
  Year = "2021"
}

@conference{ Agostinelli2021Admissible,
  Title = "Obtaining Approximately Admissible Heuristic Functions through Deep Reinforcement Learning and {A}* Search",
  Author = "Forest Agostinelli and Stephen McAleer and Alexander Shmakov and Roy Fox and Marco Valtorta and Biplav Srivastava and Pierre Baldi",
  Booktitle = "Bridging the Gap between AI Planning and Reinforcement Learning workshop (PRL @ ICAPS)",
  Year = "2021"
}

@conference{ McAleer2021CFRDO,
  Title = "{CFR-DO}: A Double Oracle Algorithm for Extensive-Form Games",
  Author = "Stephen McAleer and JB Lanier and Pierre Baldi and Roy Fox",
  Booktitle = "Reinforcement Learning in Games workshop (RLG @ AAAI)",
  Year = "2021"
}

@conference{ Fox2019EQL,
  Title = "Toward Provably Unbiased Temporal-Difference Value Estimation",
  Author = "Roy Fox",
  Booktitle = "Optimization Foundations for Reinforcement Learning workshop (OPTRL @ NeurIPS)",
  Year = "2019"
}

@unpublished{ McAleer2021Mediator,
  Title = "Improving Social Welfare while Preserving Autonomy via a Pareto Mediator",
  Author = "Stephen McAleer and JB Lanier and Michael Dennis and Pierre Baldi and Roy Fox",
  Note = "arXiv preprint \href{https://arxiv.org/pdf/2106.03927.pdf}{arXiv:2106.03927}",
  Year = "2021"
}