ConceptAI & ML
Model-based reinforcement learning version 2.5
An iterative RL algorithm that collects data with a policy, learns a dynamics model, generates synthetic trajectories using the model, and updates the policy 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
3The lectures that define it or assume it, and the concepts next to it.