How to Perform Gradient Descent for DQN Loss Function

2 visualizaciones (últimos 30 días)

Sherry X el 10 de Mzo. de 2020

Editada: Sherry X el 10 de Mzo. de 2020

I'm writing the DQN from scratch, and I'm confused of the procedure of updating the evaluateNet from the gradient descent.

The standard DQN algorithm is to define two networks:

. Train

with minibatch, and update the

with gradient descent step on

I define

. When update the

, I first make the

, and then only update

, which guarantee the

. Then I update the

. If I choose the feedforward train method as '

', does [1] update the evalNet correctly via gradient descent?

Más información sobre Deep Learning Toolbox en Help Center y File Exchange.

Find the treasures in MATLAB Central and discover how the community can help you!

Translated by