Hello,
It is my first time to write for getting help my problem which makes me waste almost a day.
There is an agent built with Python 3.6 and Pytorch 1.4 and an environment for multiple elevators.
First of all, I build a very simple DQN agent and ran it through RDP(Windows 10 Remote Desktop).
The agent has not been trained after I exit the RDP. As soon as I enter RDP, it starts running again.
I thought it caused by a sleeping mode problem from Windows 10. But I checked all of the configurations a few times. And I tested a simple program and ended up knowing for my ML agent to stop running during the user is locked.
How can I solve this problem? I tried finding similar cases over the internet but I couldn’t find any solution for it. Please help me and have a nice day !!!