8000 The implementation seems to be different from the method in the paper · Issue #70 · nv-tlabs/ASE · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

The implementation seems to be different from the method in the paper #70

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
Open
zmccmzty opened this issue Jan 17, 2024 · 2 comments
Open

The implementation seems to be different from the method in the paper #70

zmccmzty opened this issue Jan 17, 2024 · 2 comments

Comments

@zmccmzty
Copy link
zmccmzty commented Jan 17, 2024 •
edited
Loading

It looks like the policy and the discriminator are trained together at the same rate with single optimizer and combined loss (https://github.com/nv-tlabs/ASE/blob/21257078f0c6bf75ee4f02626260d7cf2c48fee0/ase/learning/ase_agent.py#L280C1-L280C1). It seems to be different from the pseudocode in the paper, where they were trained separately. Any idea about what's the reason for this? Or am I missing something?
@Winston-Gu
Copy link

I have the same question here ...

@xiaotangzh
Copy link

See last sentence of Section 2 in AMP paper: "Our motion prior also does not require a separate pre-training phase, and instead, can be trained jointly with the policy."

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
3 participants
@xiaotangzh @zmccmzty @Winston-Gu
0