[tinker] Support PPO loss with Tinker and add critic model in SkyRLTrainBackend#1389
Open
tamoghnokandar wants to merge 3 commits intoNovaSky-AI:mainfrom
Open
[tinker] Support PPO loss with Tinker and add critic model in SkyRLTrainBackend#1389tamoghnokandar wants to merge 3 commits intoNovaSky-AI:mainfrom
tamoghnokandar wants to merge 3 commits intoNovaSky-AI:mainfrom
Commits
Commits on Mar 25, 2026
- authored andcommitted


- authored andcommitted


Commits on Mar 26, 2026
- authored andcommitted

