BigBadBurrow
BigBadBurrow
Thanks @AndreasFdev, I concluded there was no way I'd be able to do training with a 4GB GPU, so I managed to lay my hands on a second-hand Titan X...
I remember that I had a problem too, so downloaded it locally and install with pip from the local download.
Okay, just beware you've hard-coded it to 2000 and it's possible to initialise players which varying stack sizes via env.add_player()
Suggested an improvement to this [here](https://github.com/wenkesj/holdem/pull/14/commits/15f68ac935cde49500a08a25d61b5a27e7517346#r255517026)
Yeah I was getting this as well with the latest code commit where you changed/added this in env.py: ``` if all([player.playedthisround for player in players]): self._resolve(players) terminal = False if...
Sorry, I wasn't up-to-speed with the changes you'd made, so you may have fixed it with the other commits you performed. I'll need to do some updates to my code.