search

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

fix: episode selection index error #331

Closed YuriCat closed 1 year ago

YuriCat commented 1 year ago

There was a possibility of stopping with an error when the buffer became short due to insufficient memory.