Dylan Hadfield-Menell is an American computer scientist and a professor of electrical engineering and computer science at the Massachusetts Institute of Technology (MIT). He leads the Algorithmic Alignment Group at MIT, studying how to make AI systems act in accordance with human intentions and values. He received his PhD from the University of California, Berkeley, advised by Anca Dragan, Pieter Abbeel, and Stuart Russell.
During his doctoral work he was first author of the 2016 papers on cooperative inverse reinforcement learning, which models human-AI cooperation as a game, and on the off-switch game, which analyzes when an AI will allow itself to be switched off.