ConceptAI & ML
Proximal policy optimization
A reinforcement learning algorithm used to fine-tune the sampling policy so that model outputs achieve high rewards.
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.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
2Each in their own terms, from the easiest level.
Nathan Lambert
An alignment method that the lecturer finds to be empirically stronger than DPO in their experiments.
Lectures that assume it
2Connections
9The lectures that define it or assume it, and the concepts next to it.