ConceptAI & ML
Experience replay
A technique in reinforcement learning where the agent stores its experiences in a memory buffer and samples random batches from it to train the network, breaking the correlation between consecutive samples.
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.
Reinforcement learning3Q-learning2Neural networks1States, actions, and rewards1Stochastic gradient descent1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
3Each in their own terms, from the easiest level.
David Silver
A technique where past experience transitions are stored in a memory buffer and sampled randomly to perform stochastic gradient descent updates.Parham Panahi
Storing raw past experiences in a memory buffer and sampling from them repeatedly to train a reinforcement learning agent.
Connections
8The lectures that define it or assume it, and the concepts next to it.