AI engineering glossary · Reinforcement learning
What is target network?
Target network: A slowly changing copy of the value network used to compute update targets, refreshed periodically or by gradual averaging. It keeps targets from shifting with every update, which reduces oscillation and divergence.
Target network: an example
Copy the online network weights to the target network every 10,000 steps.
Related terms
More Reinforcement learning terms
- TD error
- TD(0)
- TD(lambda)
- Temporal-difference learning
- Terminal state
- Thompson sampling
- Transition probability
- Twin delayed DDPG
Where you learn it
Target network is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.