ConceptAI & ML
Group relative policy optimization
GRPO is an optimization method that ranks responses within a group using relative quality as feedback to provide richer, more fine-grained feedback.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Lecturers
1Connections
3The lectures that define it or assume it, and the concepts next to it.