Brad Knox

Brad Knox is a Research Associate Professor of Computer Science at The University of Texas at Austin whose research spans reinforcement learning, human–computer interaction, and value-aligned reward specification. His doctoral work at UT Austin pioneered reinforcement learning from human feedback (RLHF), and his recent research and talks focus on using RLHF and related methods to align AI agents’ objectives with human interests.

No endorsements yet.

Personal Website

https://bradknox.net/

LinkedIn

-

Twitter / X

-

LessWrong

-

EA Forum

-

No grants recorded.