Pierre-Luc Bacon

I'm an Assistant Professor at the University of Montreal's DIRO, and I hold a Facebook CIFAR AI Chair. I'm also a member of Mila and the Institute for Data Valorization (IVADO). I specialize in developing practical deep reinforcement learning methods through the lens of representation learning and optimization techniques, applying these to real-world challenges in health, environmental sustainability, and drug design to enhance AI's practical impact. My research, which was the focus of my PhD thesis under the supervision of Doina Precup and later in my postdoctoral work with Emma Brunskill, pertains to overcoming the curse of horizon when planning and learning over long time spans. My recent work focuses on learning world models in continuous time, employing decision-aware methods, and exploring the synergy between sequence modeling and reinforcement learning to effectively address these challenges.