Joar Skalse
DPhil Scholar – Email
Joar is a DPhil student at the Department of Computer Science, supervised by Professor Alessandro Abate.
His research is on machine learning, and how to make AI systems safe and reliable. His thesis title is “Misspecification and Partial Identifiability in Inverse Reinforcement Learning”, and most of his current research is aimed towards building a formal theory of reward learning. His broader interests includes fields such as cognitive science, formal epistemology, philosophical decision theory, and computational learning theory.
Before starting his DPhil he completed the BA and MCompPhil in Computer Science and Philosophy at Oxford, which he graduated from as top of the year.