How to Perform Gradient Descent for DQN Loss Function

2 次查看（过去 30 天）

Sherry X 2020-3-10

编辑： Sherry X 2020-3-10

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?

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

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

Translated by