ConceptAI & ML
Model-free reinforcement learning
Reinforcement learning where the agent does not try to explicitly understand the environment's dynamics, going directly to the policy or value function.
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.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
2Each in their own terms, from the easiest level.
David Silver
Andrea Zanette
Reinforcement learning approach where value functions or policies are estimated directly without learning an explicit transition model of the environment.
Lectures that assume it
2Connections
15The lectures that define it or assume it, and the concepts next to it.