lukaskocian

Results 4 comments of lukaskocian

ValueError: Expected parameter loc (Tensor of shape (64, 1)) of distribution Normal(loc: torch.Size([64, 1]), scale: torch.Size([64, 1])) to satisfy the constraint Real(), but found invalid values:

UPDATE: I found out that the problem is caused by reward function, which I have rewritten to Calmar Ratio. So when I run the script with reward as portfolio value...

ValueError: Expected parameter loc (Tensor of shape (64, 1)) of distribution Normal(loc: torch.Size([64, 1]), scale: torch.Size([64, 1])) to satisfy the constraint Real(), but found invalid values:

The error was fixed by making a change in calculation of the reward. If there was a zero in denominator, divide by one.

mujoco1.50 - Could not find GCC executable.

Hello Jason, have you ended up fixing the problem? I got totally the same and can't get my head around it.

Anyone knows how to run trained models?

I spend hours understanding the code and created my own evaluation system using choose_action function