Issue during training

[anilkurkcu]

❓ Question

I am getting this error message when using SAC always at approx. 180000 time step:

ValueError: Expected parameter loc (Tensor of shape (1, 50)) of distribution Normal(loc: torch.Size([1, 50]), scale: torch.Size([1, 50])) to satisfy the constraint Real(), but found invalid values:
tensor([[nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan,
nan, nan]], device='cuda:3')

Any advice?

Checklist

• I have checked that there is no similar issue in the repo
• I have read the documentation
• If code there is, it is minimal and working
• If code there is, it is formatted using the markdown code blocks for both code and stack traces.

[qgallouedec]

Hi, we need more information to answer you. I suggest you to use the bug report template instead. Unless you are using a custom env, then use the custom env template.

[araffin]

Probably a duplicate of DLR-RM/rl-baselines3-zoo#156 (comment)