ConceptAI & ML
Action-value actor-critic
An actor-critic algorithm that uses an action-value function approximation to evaluate the policy and update the critic parameters via linear TD(0) and the actor parameters via policy gradient.
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
4The lectures that define it or assume it, and the concepts next to it.