Are the experiments working?

[bborj]

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]

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"