@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{ McAleer2020Pipeline,
  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{ Bavishi2019AutoPandas,
  Title = "Auto{P}andas: Neural-Backed Generators for Program Synthesis",
  Author = "Rohan Bavishi and Caroline Lemieux and Roy Fox and Koushik Sen and Ion Stoica",
  Booktitle = "10th ACM SIGPLAN Conference on Systems, Programming, Languages, and Applications: Software for Humanity (SPLASH OOPSLA)",
  Year = "2019"
}

@conference{ Fox2019Multi,
  Title = "Multi-Task Hierarchical Imitation Learning for Home Automation",
  Author = "Roy Fox and Ron Berenstein and Ion Stoica and Ken Goldberg",
  Booktitle = "15th IEEE Conference on Automation Science and Engineering (CASE)",
  Year = "2019"
}

@conference{ McAleer2022Anytime,
  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{ Liang2021Temporal,
  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{ Hu2021Count,
  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{ Xu2021Target,
  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{ Agostinelli2021Obtaining,
  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{ Nottingham2021Modular,
  Title = "Modular Framework for Visuomotor Language Grounding",
  Author = "Kolby Nottingham and Litian Liang and Daeyun Shin and Charless C. Fowlkes and Roy Fox and Sameer Singh",
  Booktitle = "Embodied AI workshop (EmbodiedAI @ CVPR)",
  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{ Fox2019Toward,
  Title = "Toward Provably Unbiased Temporal-Difference Value Estimation",
  Author = "Roy Fox",
  Booktitle = "Optimization Foundations for Reinforcement Learning workshop (OPTRL @ NeurIPS)",
  Year = "2019"
}

@conference{ Yan2019Multi,
  Title = "Multi-Task Learning via Task Multi-Clustering",
  Author = "Andy Yan and Xin Wang and Ion Stoica and Joseph Gonzalez and Roy Fox",
  Booktitle = "Adaptive \& Multitask Learning workshop (AMTL @ ICML)",
  Year = "2019"
}

@unpublished{ McAleer2021Improving,
  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"
}

@unpublished{ Agostinelli2021Astar,
  Title = "{A}* Search Without Expansions: Learning Heuristic Functions with {D}eep {Q}-{N}etworks",
  Author = "Forest Agostinelli and Alexander Shmakov and Stephen McAleer and Roy Fox and Pierre Baldi",
  Note = "arXiv preprint \href{https://arxiv.org/pdf/2102.04518.pdf}{arXiv:2102.04518}",
  Year = "2021"
}

@unpublished{ Fox2019Hierarchical,
  Title = "Hierarchical Variational Imitation Learning of Control Programs",
  Author = "Roy Fox and Richard Shin and William Paul and Yitian Zou and Dawn Song and Ken Goldberg and Pieter Abbeel and Ion Stoica",
  Note = "arXiv preprint \href{https://arxiv.org/pdf/1912.12612.pdf}{arXiv:1912.12612}",
  Year = "2019"
}