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.

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

Controller Input #36

Open
zhefan opened this issue Nov 13, 2020 · 1 comment
Open

Controller Input #36

zhefan opened this issue Nov 13, 2020 · 1 comment

Comments

@zhefan
Copy link

zhefan commented Nov 13, 2020

Hi, I wonder if the input to the controller should be the latent vector (z) from VAE and hidden vector from RNN?

_, _, _, _, _, next_hidden = self.mdrnn(action, latent_mu, hidden)

But the code here shows that one of the inputs is the gaussian mean instead.

@pdeubel
Copy link

pdeubel commented Feb 24, 2022

Yes I though the same, as it turns out there was already a discussion about this in #28. Seems like it does not affect the performance of that particular environment, nevertheless I think the correct latent vector z should be used

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants