Description Usage Arguments Details
View source: R/AsynchronousAdvantageActorCritic.R
Defines a tensorflow graph to update Network parameters based on the gradients w.r.t to the loss function.
1 | Define_Graph_Gradient_Update(model, model.par)
|
model |
A Neural Network e.g. as given by |
model.par |
A list with parameters to set up the Network e.g. as given by |
Returns a list of tensors and placeholders
gradients.update Calculate updated weights based on provided gradients.
vars.grads.pl Placeholders for the gradients.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.