Skip to content

feat(ppo): warm-start the value model from a critic-pretrain checkpoint - #3821

Merged
terrykong merged 6 commits into
mainfrom
yukih/sc-warm-start-critic
Aug 28, 2026
Merged

feat(ppo): warm-start the value model from a critic-pretrain checkpoint#3821
terrykong merged 6 commits into
mainfrom
yukih/sc-warm-start-critic

test(sc): assert the empty warm-start message on its own parametrization

c39b179
Select commit
Loading
Failed to load commit list.
DCO / DCO succeeded Aug 28, 2026 in 0s

DCO

All commits are signed off!