DeNA / HandyRL

HandyRL is a handy and simple framework based on Python and PyTorch for distributed reinforcement learning that is applicable to your own environments.
MIT License
282 stars 41 forks source link

(Idea) feature: daemonic threads & daemonic batcher processes & wait stopping workers #307

Closed YuriCat closed 2 years ago

YuriCat commented 2 years ago

Can this implementation easily finish every process?

ikki407 commented 2 years ago

This feature is verified and finished correctly in my several games.