feature: eval_rate -> eval_coef

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

feature: eval_rate -> eval_coef #329

Open YuriCat opened 1 year ago

YuriCat commented 1 year ago

eval_rate was not practically useful. eval_coef will be better, and it can be hidden config argument.