Henry Papadatos

Henry is currently finishing his master’s degree in robotics and data science at the Swiss Federal Institute of Technology Lausanne (EPFL). Where he also co-founded and organized the Lausanne AI alignment team. Being interested by the governance aspect of AI as well, he is a co-author of the «Navigating AI risks» newsletter.
At CHAI, Henry will work on reinforcement learning from human preferences (RLHP). He will identify and demonstrate shortcomings in RLHP that can lead to dangerous reward learning failures, then propose solutions to make RLHP more safe and robust. His work will be supervised by Rachel Freedman.