Scientific originatorTraining-method researcher

John Schulman

Thinking Machines Lab

ORCID lookup ↗DBLP lookup ↗Scholar lookup ↗Semantic Scholar ↗arXiv ↗GitHub ↗

Developed core policy-optimization methods for RLHF and studied reward overoptimization central to aligning language models.

Works in the archive (4)

“Lead” marks the first-listed author — a byline fact, not a measure of influence; co-authorship is shown as recorded.

Co-authors in the archive

Karl Cobbe (2), Jacob Hilton (2), Vineet Kosaraju, Dan Hendrycks, Jacob Steinhardt, Reiichiro Nakano, Suchir Balaji, Leo Gao, Mrinank Sharma, Ethan Perez, Hunter Lightman, Ilya Sutskever

View co-author network (14 people)

Loading graph…