ConceptAI & ML
Dyna architecture
An architecture that integrates model learning, direct reinforcement learning, and planning by using both real and simulated experience to learn value functions and policies.
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.
Model-based RL1Model-free RL1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
1Connections
4The lectures that define it or assume it, and the concepts next to it.