uvipen / Super-mario-bros-A3C-pytorch

Asynchronous Advantage Actor-Critic (A3C) algorithm for Super Mario Bros

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Would you please tell me how long this code run to train a stable A3C agent?

wangxiao5791509 opened this issue · comments

Hi, nice job. I wonder try this code. Would you please tell me how long this code need to run to train a stable A3C agent? Thanks.

Hi,
It took me about 6-12 hours for each level.

@vietnguyen91 Thanks for your information. I will try this later. Thank you.