Google Scholar

Publications

• Feasible Adversarial Robust Reinforcement Learning for Underspecified Environments. (In submission).
  JB Lanier, Stephen McAleer, Pierre Baldi, Roy Fox.
• Self-Play PSRO: Toward Optimal Populations in Two-Player Zero-Sum Games. (In submission).
  Stephen McAleer, JB Lanier, Kevin Wang, Pierre Baldi, Roy Fox, Tuomas Sandholm.
• Anytime PSRO for Two-Player Zero-Sum Games. (In submission).
  Stephen McAleer, Kevin Wang, JB Lanier, Marc Lanctot, Pierre Baldi, Tuomas Sandholm, Roy Fox.
• XDO: A Double Oracle Algorithm for Extensive-Form Games. NeurIPS 2021.
  Stephen McAleer, JB Lanier, Kevin Wang, Roy Fox, Pierre Baldi.
• Improving Social Welfare While Preserving Autonomy via a Pareto Mediator. preprint (2021).
  Stephen McAleer, JB Lanier, Michael Dennis, Pierre Baldi, Roy Fox.
• OffWorld Gym: Open-Access Physical Lunar Analog Environment for Reinforcement Learning and Robotics Research. 43rd COSPAR Scientific Assembly (2021).
  Ashish Kumar, Toby Buckley, JB Lanier, Qiaozhi Wang, Alicia Kavelaars, Ilya Kuzovkin.
• Pipeline PSRO: A Scalable Approach for Finding Approximate Nash Equilibria in Large Games. NeurIPS 2020.
  Stephen McAleer*, JB Lanier*, Roy Fox, Pierre Baldi (*equal contribution).
• ColosseumRL: A Framework for Multiagent Reinforcement Learning in N-Player Games. COMARL AAAI 2020.
  Alex Shmakov, JB Lanier, Stephen McAleer, Rohan Archar, Cristina Lopes, Pierre Baldi.
• Curiosity-Driven Multi-Criteria Hindsight Experience Replay. NeurIPS 2019 Deep RL Workshop.
  JB Lanier, Stephen McAleer, Pierre Baldi.