Jonathan Colaço Carr

I think AI will be one of the most important factors to the wellbeing of future generations, and we need to make sure that we understand how this technology acts in the real world.

I’m interested in how reinforcement learning agents behave in large, unknown environments. I often consider these agents in the context of the AI alignment problem.

Outside of Mila, I’ve worked on AltaML’s applied AI team, done research in quantum information theory, co-hosted EA x Law, and taken the OFTW pledge.