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 42 forks source link

feature: use set instead of list for connections in QueueCommunicator #309

Closed YuriCat closed 2 years ago

YuriCat commented 2 years ago

set.discard(a) doesn't raise unfound error.

ikki407 commented 2 years ago

Thanks!