Justin Svegliato

Justin is a Research Scientist in the Center for Human-Compatible AI at UC Berkeley. He received his PhD in Computer Science at UMass Amherst where he was advised by Shlomo Zilberstein. The goal of his research is to build autonomous systems that operate in the open world for long periods of time in an efficient, reliable, and ethical way. Recently, his work has focused on ensuring that autonomous systems comply with different ethical theories, such as utilitarianism, Kantianism, and prima facie duties. His work has also focused on using metareasoning to enable autonomous systems to recover from exceptions, maintain and restore safe operation, and optimize the performance of anytime planning algorithms for bounded rationality. You can learn more about Justin at his website.