ConceptAI & ML
Batch reinforcement learning
Batch methods seek to find the best fitting value function given all of the agent's experience as training data.
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.
Experience data1Gradient descent1Gradient descent method1Monte Carlo1Reinforcement learning1TD learning1Value function approximation1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
1David Silver
Connections
7The lectures that define it or assume it, and the concepts next to it.