ConceptAI & ML
Greedy policy improvement over Q
A model-free method of improving a policy by selecting the action that maximizes the action-value function Q.
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.
Action-value function Q1Policy improvement1
Lecturers
1Connections
2The lectures that define it or assume it, and the concepts next to it.