EECS Colloquium: Reinforcement Learning from Human Feedback

Colloquium | April 19 | 5-6 p.m. | Sutardja Dai Hall, 310 Sutardja Dai Hall

Speaker/Performer:  John Schulman, OpenAI

Sponsors:  Electrical Engineering and Computer Sciences (EECS), Berkeley Artificial Intelligence Research

Biography

John Schulman received a Ph.D. from Berkeley EECS in 2016, advised by Pieter Abbeel. He now leads a team working on ChatGPT and RL from Human Feedback at OpenAI, where he was a co-founder. His previous work includes foundational algorithms of deep RL (TRPO, PPO), generalization in RL (ProcGen), mathematical reasoning by language models (GSM8K), combining RL with retrieval (WebGPT) and studying scaling laws of RL and alignment. In his free time, he enjoys running, jazz piano, and raising chickens.

Event Contact:  jennyj@berkeley.edu, 510 643-0855

Access Coordinator:  Jenny Jones,  jennyj@berkeley.edu,  510-643-0855

To share this video via email, copy and paste the message and URL below into your favorite email client and send.