@conference{ Liang2022Reducing,
  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{ Nottingham2022Learning,
  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{ Fox2022Independent,
  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{ 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{ Lanier2022Feasible,
  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{ 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{ 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"
}

@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"
}