ConceptAI & ML
Model-based reinforcement learning version 2.0
An algorithm that alternates between collecting data with a policy, learning a dynamics model, and backpropagating through the dynamics model directly into the policy parameters to optimize them.
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.