Toggle navigation
Login
Dashboard
Login
Dashboard
Home
About
A Brief History of AI
AI-Alerts
AI Magazine
AAAI Conferences
NeurIPS
Books
Classics
Toggle navigation
Login
Dashboard
Home
About
A Brief History of AI
AI-Alerts
AI Magazine
AAAI Conferences
NeurIPS
Books
Classics
Login
Toggle navigation
Login
Dashboard
Home
About
A Brief History of AI
AI-Alerts
AI Magazine
AAAI Conferences
NeurIPS
Books
Classics
Login
Toggle navigation
Login
AITopics
An official publication of the AAAI.
powered by
i
2
k
Connect
Login
Toggle navigation
Login
Dashboard
AITopics
An official publication of the AAAI.
Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification
Open in new window
aitopics.org uses cookies to deliver the best possible experience. By continuing to use this site, you consent to the use of cookies.
Learn more ยป
I understand
×
Add feedback
Send feedback to help us improve this new enhanced search experience.
Select feedback type:
General
views
title
summary
body
concept tags
oilfield places
Thank you!