ConceptAI & ML
Approximate Q-learning
Q-learning where the Q-value function is parameterized by weights over features rather than stored in a table.
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
2Each in their own terms, from the easiest level.
Pieter Abbeel & Daniel Klein
A reinforcement learning method that uses feature representations to approximate Q-values for state-action pairs.
Connections
6The lectures that define it or assume it, and the concepts next to it.