ConceptAI & ML
REINFORCE
A Monte-Carlo policy gradient algorithm that updates parameters by stochastic gradient ascent using the return as an unbiased sample of the action-value function.
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
1Lectures that assume it
2Connections
8The lectures that define it or assume it, and the concepts next to it.