Dylan Cope

Dylan Cope is a third year PhD student at King’s College London with the Safe and Trusted AI CDT, and a visiting doctoral student at Imperial College London. His doctoral research focuses on explainee-centric explanation in the context of multi-agent communication, with applications to the AI alignment problem. Outside of his PhD he has conducted research on robustness to distributional shift, transfer learning, and emergent communication in reinforcement learning. Previously, he worked as an applied AI data scientist and a software engineer. At CHAI, Dylan will be working with Justin Svegliato on metareasoning in reinforcement learning.