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

State (cent obs) not used in evaluate actions #30

Open
brithbutter opened this issue Feb 22, 2024 · 1 comment
Open

State (cent obs) not used in evaluate actions #30

brithbutter opened this issue Feb 22, 2024 · 1 comment

Comments

@brithbutter
Copy link

To whom it may concern,
I noticed that in forward() of ma_transformer.py, the state (cent obs) is converted into zeros. However, it seems to be an essential element for critic function of the RL. And I roughly can not identify the reason or explanation about this in the paper. Could you provide an elaboration in code?
Sincerely,

@morning9393
Copy link
Collaborator

hiya, thx for your attention, the cent obs is a redundant parameter in MAT (just used for debugging, I forgot to delete it). In MAT, the encoder will combine obs from all agents, performing the role of cent obs (but including less information than cent obs, if you are chasing the ultimate performance, you could also replace the obs with cent obs for encoder I think~).

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