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

Why trained policy is not as good as yours #18

Open
gwhan98 opened this issue Jan 27, 2021 · 1 comment
Open

Why trained policy is not as good as yours #18

gwhan98 opened this issue Jan 27, 2021 · 1 comment

Comments

@gwhan98
Copy link

gwhan98 commented Jan 27, 2021

Hi, I followed all your steps and trained the policy from scratch for stage 1.

I am not able to get a policy as good as yours (still always crashes) even after training for 12 hours.

May I ask if you used anything special to train the policy? I have tried many times but cannot get a good policy, and starting from scratch seems very bad.

@Acmece
Copy link
Owner

Acmece commented Jan 28, 2021

It's hard to say.
You may train a longer time to see the performance.
I have used three machines for distributed training, for your information.

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