Nicolas Usunier

Nicolas Usunier joined Facebook as a Research Scientist in March 2015. Nicolas received his PhD in Machine Learning from Université Pierre et Marie Curie, in Paris, in 2006. Nicolas was an Associate Professor there until 2012, when he joined Université de Technologie de Compiègne, France, with a chair position from the CNRS-Higher Education Chairs program. Nicolas' research interests are learning theory, learning to rank, and learning with multiples objectives.

Nicolas' Publications

June 19, 2020

RESEARCH

A Structured Prediction Approach for Generalization in Cooperative Multi-Agent Reinforcement Learning

Effective coordination is crucial to solve multi-agent collaborative (MAC) problems. While centralized reinforcement learning methods can optimally solve small MAC instances, they do not scale to large problems and they fail to generalize to scenarios different from those seen during training. In this paper, we consider MAC problems with some…

Nicolas Carion, Gabriel Synnaeve, Alessandro Lazaric, Nicolas Usunier

June 19, 2020

June 19, 2020

RESEARCH

Value Propagation Networks

We present Value Propagation (VProp), a set of parameter-efficient differentiable planning modules built on Value Iteration which can successfully be trained using reinforcement learning to solve unseen tasks, has the capability to generalize to larger map sizes, and can learn to navigate in dynamic environments. We show that the modules enable…

Nantas Nardelli, Gabriel Synnaeve, Zeming Lin, Pushmeet Kohli, Philip H.S. Torr, Nicolas Usunier

June 19, 2020

June 19, 2020

RESEARCH

Forward Modeling for Partial Observation Strategy Games – A StarCraft Defogger

We formulate the problem of defogging as state estimation and future state prediction from previous, partial observations in the context of real-time strategy games. We propose to employ encoder-decoder neural networks for this task, and introduce proxy tasks and baselines for evaluation to assess their ability of capturing basic game rules and…

Gabriel Synnaeve, Zeming Lin, Jonas Gehring, Dan Gant, Vegard Mella, Vasil Khalidov, Nicolas Carion, Nicolas Usunier

June 19, 2020