Closed marbrink closed 5 years ago
Did you modified and saved some scripts as the training was ongoing ?
If yes, it's what caused this error.
You can always restart the training where it stopped by adding --load when you relaunch your training in the python/anaconda window. Just place it before the --training.
I believe I have ran into the same issue. I left my computer idle for a few hours and when I came back I got this error.
This issue has been automatically marked as stale because it has not had activity in the last 14 days. It will be closed in the next 14 days if no further activity occurs. Thank you for your contributions.
I also get NullReferenceException: Object reference not set to an instance of an object when trying to run the hallway example.
This issue has been automatically marked as stale because it has not had activity in the last 14 days. It will be closed in the next 14 days if no further activity occurs. Thank you for your contributions.
This issue has been automatically closed because it has not had activity in the last 28 days. If this issue is still valid, please ping a maintainer. Thank you for your contributions.
This thread has been automatically locked since there has not been any recent activity after it was closed. Please open a new issue for related bugs.
During training I sometimes get this repeating error in my console and the agent doesn't do anything anymore. It happens seamingly at random, sometimes after 20k steps, sometimes after 200k steps sometimes not at all. I've had it happen in my self-designed environment and I've had this happen in example environments, i.e. just now it happened in the "Hallway"-Environment. I'm on ml-agents 0.81.
The complete error is as follows: NullReferenceException: Object reference not set to an instance of an object MLAgents.Academy.EnvironmentStep () (at Assets/ML-Agents/Scripts/Academy.cs:579) MLAgents.Academy.FixedUpdate () (at Assets/ML-Agents/Scripts/Academy.cs:655)