-
Notifications
You must be signed in to change notification settings - Fork 9
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
NaN #5
Comments
Yes, that's a list of the actions going to each agent, which I printed out for debugging purposes. I have seen the actions all go to NaN values, and haven't yet found a reason (or solution) to that. If you do, please update this thread! |
I determined that something is going wrong with the numerical computation of relu. Change all instances of relu to tanh or sigmoid as hidden layer neurons and you won’t see that error any longer. |
Did you try to use the relu with the batch normalization? It looks that now NaN have disappeared. |
@farice Changing relu to tanh does not improve the situation for me, rewards still go to NaN after a while. Did you make any other changes as well? |
If I change relu to tanh, the training has been running for almost 3 days and NaN have not appeared (neither in the actions or rewards). Looks like it also works when I use the relu, but it needs adding the batch normalization. |
After a sufficient number of steps, I'll get an array full of nans when running your sample script. Have you seen this before?
The text was updated successfully, but these errors were encountered: