ConceptAI & ML
COMBO
An algorithm that applies a conservative Q-learning (CQL) principle to model-based offline reinforcement learning by penalizing Q-values of model state-action tuples.
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.