Skip to content

(Idea) feature: update configuration for turn-based#241

Open
YuriCat wants to merge 6 commits intoDeNA:developfrom
YuriCat:feature/update_configuration_for_turn_based_games
Open

(Idea) feature: update configuration for turn-based#241
YuriCat wants to merge 6 commits intoDeNA:developfrom
YuriCat:feature/update_configuration_for_turn_based_games

Conversation

@YuriCat
Copy link
Copy Markdown
Contributor

@YuriCat YuriCat commented Jan 22, 2022

Turn-based batch creation and zero-sum averaging are different and independent.
Moreover, these should be set False at default for safety.

handyrl/train.py Outdated
@@ -165,7 +165,10 @@ def forward_prediction(model, hidden, batch, args):
o = o.view(*batch['turn_mask'].size()[:2], -1, o.size(-1))
if k == 'policy':
# gather turn player's policies
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This comment and line 170 comment is duplicated.

@ikki407
Copy link
Copy Markdown
Member

ikki407 commented Jan 24, 2022

Thank you, it becomes that the two functions can be totally understood and easy to be used by users.

@ikki407
Copy link
Copy Markdown
Member

ikki407 commented Jan 24, 2022

Could you update parameters.md?
https://github.com/DeNA/HandyRL/blob/master/docs/parameters.md

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants