Reinforcement Learning from Human Feedback: Progress and Challenges

XRG is the EECS department's primary interface with the general public.  They manage theCorporate Access Program(CAP)--which offers first tier access to our graduating students for institutions who donate to the department annually; alumni relations; the EECS Joint Colloquium;  theBerkeley EECS Annual Research Symposium(BEARS); the Industrial Advisory Board(IAB); and all public relations matters.

External Relations Group, EECS

A Distinguished Lecture  by John Schulman from OpenAI  on the Reinforcement Learning from Human Feedback (RLHF) work powering ChatGPT.

Banatao Auditorium

Speaker Biography:John received a PhD in the EECS department at Berkeley 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 cofounder. 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.P﻿lease note: if you would like to watch John&#x27;s talk remotely, you need not register. Tickets here are for in-person attendance only, for which there is very limited seating.You will find the talk streaming here: <a href="https://www.youtube.com/c/UCBerkeleyEECSEvents/live" target="_blank" data-msys-clicktrack="0" rel="nofollow noopener noreferrer">https://www.youtube.com/c/UCBerkeleyEECSEvents/live</a><a href="https://www.youtube.com/@UCBerkeleyEECSEvents/streams" target="_blank" data-msys-clicktrack="0" rel="nofollow noopener noreferrer"></a>

Our {communityGuidelinesLink} describe the sort of content we prohibit on Eventbrite. If you suspect an event may be in violation, you can report it to us so we can investigate.

To report other categories of prohibited or illegal content, submit {link}

Reinforcement Learning from Human Feedback: Progress and Challenges

More events from External Relations Group, EECS

Discover more events from External Relations Group, EECS, from Science & Tech to other experiences you might love.

Reinforcement Learning from Human Feedback: Progress and Challenges

More events from External Relations Group, EECS

Discover more events from External Relations Group, EECS, from Science & Tech to other experiences you might love.

You might also like...

Browse more events with different dates, prices, and formats to find your next great experience.