magenta/magenta

Make it easier to use different reward functions in rl_tuner

Open

#375 opened on 2016年11月10日

GitHub で見る
 (1 comment) (1 reaction) (0 assignees)Python (18,909 stars) (3,723 forks)batch import
help wanted

説明

The reward calculation code should be factored out into a separate class that implements an interface. This would make it easier for users to create their own reward implementations.

コントリビューターガイド