Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Normalize actor gradients? #15

Open
panjiangwei opened this issue Oct 11, 2018 · 1 comment
Open

Normalize actor gradients? #15

panjiangwei opened this issue Oct 11, 2018 · 1 comment

Comments

@panjiangwei
Copy link

This gradient for actor needs to be normalized over batch_size?

DDPG/actor_network_bn.py

Line 37 in 18825ee

self.parameters_gradients = tf.gradients(self.action_output,self.net,-self.q_gradient_input)

@j314erre
Copy link

j314erre commented Feb 1, 2019

I have the same question, since I've seen implementations that normalize these gradients. However, if batch size is always the same constant, then it doesn't matter that much and you can just adjust the learning rate, right?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@panjiangwei @j314erre