Panels

Panel 1: High-Impact Applications of RL

Cathy Wu

MIT

Stefano Albrecht

University of Edinburgh

Omer Gottesman

Amazon

Pablo Samuel Castro

Google Deepmind and Université de Montréal

The Limits of Reward Functions

Anna Harutyunyan

Google Deepmind

David Abel

Google Deepmind

Dylan Hadfield-Menell

MIT

James MacGlashan

Sony AI

Serena Booth

Brown and AAAS AI Policy Fellow