ConceptAI & ML
Dyna-Q
An algorithm that integrates model-learning, direct reinforcement learning, and planning updates to update action-value functions and models simultaneously.
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
5The lectures that define it or assume it, and the concepts next to it.