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

Are the experiments working? #144

Open
bborj opened this issue Feb 9, 2023 · 2 comments
Open

Are the experiments working? #144

bborj opened this issue Feb 9, 2023 · 2 comments

Comments

@bborj
Copy link

bborj commented Feb 9, 2023

Hi,

I have run the experiment that appears in the readme, and i do not even know if the experiment work. It has been for like 6 hours training with Starcraft opened, but not logs were raised on terminal, it just opened SC2 and started playing games, i checked and inside the results some metrics were saved, like the duration of the episode, etc. But for example the file "cout" is empty. As i said, it started running, then it finished, but no logs where shown, just the first one saying that the results were going to be saved at the results path. I am not that good with Sacred, in case it is working, how could i modify the qmix algorithm in order to make it self-supervised?

Thanks!

@bborj
Copy link
Author

bborj commented Feb 10, 2023

Regarding this, i looked into the "run.json", and it seems that it failed after some hours. The fail trace is like this:
"Traceback (most recent call last):\n", " File pymarl\\lib\\site-packages\\sacred\\config\\captured_function.py\", line 42, in captured_function\n result = wrapped(*args, **kwargs)\n", " File \"main.py\", line 35, in my_main\n run(_run, config, _log)\n", " File \\pymarl\\src\\run.py\", line 51, in run\n print(\"Exiting Main\")\n", "OSError: [WinError 1] Funci\u00f3n incorrecta\n"

@wadith027
Copy link

Same here! Did you get any workaround after that?

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