ConceptAI & ML
Reinforcement learning (RL) in LLMs
A trial-and-error learning process where a model generates multiple solutions, checks them against correct answers, and reinforces the token sequences that lead to correct solutions.
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.