Roman Ring

thanks, will fix asap

hey @fredluhamaa as you can probably guess my schedule is a bit busy :) Fixing this and some other issues have been on my mind, but I can't give you...

Good catch, thanks. I have plans to simplify/refactor API soon, will look into it then

It's probably an incompatibility with the newer TensorFlow versions, try pinning it to 2.1.x.

Hello, 1. A dedicated config shouldn't be necessary as the model weights were trained with the provided configs (although that *might* have changed, will need to double check). 2. This...

which PySC2 version do you have?

I can confirm the first one, though it's actually a `FutureWarning`, not an error (e.g. doesn't prevent the code from running). Unfortunately, it's happening inside PySC2, so I can't really...

@EvanWilliams thank you for the kind words! I'm happy to hear you've found reaver useful :)

Hello Dohyeong, I assume you're trying to replicate the AlphaStar architecture? First, note that spatial information is still processed by a normal conv model and transformer body is applied only...

Hello, from what you're showing it seems to be working fine. If it's completely stuck for longer than a couple of minutes then try re-running, SC2 client itself can sometimes...