Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
2025-01-22
· ICLR 2025 Poster ·
anchor
Findings
IC-146
Pythia models show increasing robustness to off-policy RLHF data as policy size scales from 410M to 2.8B