BigBadBurrow

Recommended GPU size when training BERT-base

7

What is the minimum GPU spec for training the base model? Obviously I realise it depends on the hyperparameters, but I have a 4GB GPU that I'm trying to train...

Environment is requesting player moves when there's only one player who is not all-in

2

I found a problem if all but one players are all-in, i.e. only one player has stack available. The environment continues to ask the player that isn't all-in for a...

reset_stack() method and self.betting appear to be redundant in player.py?

2

reset_stack() method doesn't appear to be referenced self.betting defined in player.py appear to be redundant (it's only ever set to False), but care needs to be taken if removed as...

Add player.currentbet to _get_current_state

1

I think it's useful information to have the player.currentbet available on player_infos: ``` player_features = [ int(player.emptyplayer), int(player.get_seat()), int(player.stack), int(player.playing_hand), int(player.handrank), int(player.playedthisround), int(player.betting), int(player.isallin), int(player.lastsidepot), int(player.currentbet), ] ```

Latest code change causes rounds to not resolve

1

In the latest code commit in `env.step()` you changed: ``` else: self._resolve(players) ``` to this: ``` if all([player.playedthisround for player in players]): self._resolve(players) ``` But rounds are getting stuck, constantly...