What is a target network?
In Deep Q-learning, a neural network that is a stable approximation of the main neural network, where the main neural network implements either a Q-function or a policy.
target network explained in plain English
In Deep Q-learning, a neural network that is a stable approximation of the main neural network, where the main neural network implements either a Q-function or a policy. Then, you can train the main network on the Q-values predicted by the target network. Therefore, you prevent the feedback loop that occurs when the main network trains on Q-values predicted by itself. By avoiding this feedback, training stability increases.
Example
Practitioners refer to target network when building, training, or evaluating machine learning systems. It appears in research papers, product documentation, and technical discussions about AI capabilities and limitations.
People also read
- Deep Q-Network
In Q-learning, a deep neural network that predicts Q-functions.
- Neural Architecture Search
A technique for automatically designing the architecture of a neural network.
- accelerator chip
A category of specialized hardware components designed to perform key computations needed for deep learning algorithms.
- action
In reinforcement learning, the mechanism by which the agent transitions between states of the environment.
- activation function
A function that enables neural networks to learn nonlinear (complex) relationships between features and the label.
- AdaGrad
A sophisticated gradient descent algorithm that rescales the gradients of each parameter, effectively giving each parameter an independent learning rate.
- Attention
A mechanism that lets a model focus on the most relevant parts of its input when producing an output, weighting what matters most in context.
- auto-regressive model
A model that infers a prediction based on its own previous predictions.
- autoencoder
A system that learns to extract the most important information from the input.
- auxiliary loss
A loss function—used in conjunction with a neural network model's main loss function—that helps accelerate training during the early iterations when weights are randomly initialized.