Pretraining Midtraining Rl Interplay

Understand when RL genuinely expands reasoning beyond pre-training through controlled experiments on synthetic tasks. Discover that RL works best at the edge of competence and process rewards reduce hacking—critical for designing effective reasoning model training.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit e27915f56f

Frequently asked questions

npx get-skill add adu2021/pretraining-midtraining-rl-interplay