CS547 Human-Computer Interaction Seminar   (Seminar on People, Computers, and Design)

Fridays 11:30am-12:30pm PT · Gates B3 · Open to the public
Previous | Next
Emma Brunskill
Stanford
Human in the Loop Reinforcement Learning
March 2, 2018

While much of artificial intelligence has focused on automating human intelligence and behavior, there exists an even more exciting parallel thread---how artificial intelligence can amplify human intelligence. We focus on advancing reinforcement learning for human-in-the-loop scenarios, where an automated agent may be helping to teach a student, work with a clinician, or benefit from other human experts. I will discuss several of our recent results and our ongoing research in this direction.


Emma Brunskill is an assistant professor of computer science at Stanford University. She is a Rhodes Scholar, a Microsoft Faculty Fellow, a NSF CAREER awardee and a ONR Young Investigator Program recipient and her group's has been recognized by multiple best paper nominations. She seeks to create interactive machine learning agents that help people realize their goals. To do this her group works on both the algorithmic and theoretical reinforcement learning challenges that arise in this pursuit, and in testing these ideas in real systems, with a particular focus on creating learning software that learns.