ConceptAI & ML
REINFORCE algorithm
A Monte Carlo policy gradient method that samples trajectories, estimates the policy gradient, and updates policy parameters via gradient ascent.
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
3Each in their own terms, from the easiest level.
David Silver
Monte-Carlo policy gradient algorithm that updates policy parameters using stochastic gradient ascent with unbiased sample returns.Fei-Fei Li, Justin Johnson & Serena Yeung
A policy gradient method that estimates the gradient of the expected reward by sampling trajectories and using the cumulative reward of each trajectory to scale the gradient of the log-probability of the actions taken.Sergey Levine
Connections
9The lectures that define it or assume it, and the concepts next to it.