ConceptAI & ML
Advantage-weighted regression (AWR) / advantage-weighted actor-critic
An algorithm that alternates between fitting a critic using standard Q-learning and updating the actor via weighted maximum likelihood using advantage weights.
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.