Sam Devlin is a Principal Researcher in the Game Intelligence group at Microsoft Research. He received his PhD on multi-agent reinforcement learning in 2013 from the University of York; was a postdoc from 2013 to 2015, working on game analytics; and then was on the faculty from 2016 until joining Microsoft in 2018. Devlin has published more than 60 papers on reinforcement learning, imitation learning and game AI in leading academic venues and presents regularly at games industry events including Develop and the Game Developers Conference (GDC).
Talk Title: Learning to Control Embodied Agents
Abstract:
A discussion on when to use imitation learning, reinforcement learning or world models to control autonomous agents embodied in complex, real-time 3D environments.
RPL Summer School 2026 