Guillaume is interested in the emergence of collaboration/cooperation in large groups of intelligent agents making individual choices, based on their local understanding of the world. In particular, his team is interested in identifying the right information and ways of processing it that allows agents to reason about and improve decentralized cooperative decision-making. His work is inscribed in the current push away from centralized methods, where a single entity/AI controls each agent in the team, and toward distributed/decentralized approaches where agents are in charge of their own destiny. To do so, his work draws from recent advances in artificial intelligence, in particular distributed deep reinforcement learning (RL), as well as from more conventional methods such as stochastic modeling and feedback control. Applications range from multi-robot systems, where independent robots need to coordinate their actions to achieve a common goal, to high-DoF articulated robots, where joints need to be carefully coupled during locomotion in rough terrain.

Guillaume was a Manufacturing Futures Initiative (MFI) postdoctoral fellow at CMU in 2018-2019, was awarded an Amazon Research Awards in 2022, as well as an Outstanding Early Career Award from NUS’ College of Design and Engineering in 2023.