ConceptAI & ML
Target network
A separate copy of the Q-function network used to compute target values that remains static for several steps to stabilize learning.
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.
Russ Tedrake
A separate copy of network parameters kept frozen or updated slowly to stabilize training by decoupling the desired targets from the parameters being optimized.
Connections
7The lectures that define it or assume it, and the concepts next to it.