Skip to content

feat(rl): add SAO synchronous training baseline with skip-observation GAE, DIS policy loss and value critic ``` - #269

Open
xxyyrr598 wants to merge 5 commits into
modelscope:mainfrom
xxyyrr598:add-sao-sync
Open

feat(rl): add SAO synchronous training baseline with skip-observation GAE, DIS policy loss and value critic ```#269
xxyyrr598 wants to merge 5 commits into
modelscope:mainfrom
xxyyrr598:add-sao-sync

feat(sao): extract reusable DIS policy objective into policy_objectiv…

bdb92b2
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning
lint
succeeded Aug 28, 2026 in 43s