Is it possible to share some experiment details about model training ?

[nicklhy]

Thanks a lot for sharing this awesome project !

I really want to have a try for the training part, but didn't find any experiment details in README or your arxiv paper. Is it possible for you to kindly share some info about the questions below ?

• How many disk/memory space should I prepare for the training part?
• How long it takes to do supervised/rl train with single or multi gpus?
• What level can the trained agent achieve? Can the trained agent beat easy/median/hard bot in sc2 ?

[liuruoze]

Hi, our journal paper has recently been notified of acceptance. I will put the arxiv version of the paper on Arxiv recently. At that time I will notify you! The journal paper contains all the experiment details! At 2022-08-24 10:59:36, "nicklhy" ***@***.***> wrote: Thanks a lot for sharing this awesome project ! I really want to have a try for the training part, but didn't find any experiment details in README or your arxiv paper. Is it possible for you to kindly share some info about the questions below ? How many disk/memory space should I prepare for the training part? How long it takes to do supervised/rl train with single or multi gpus? What level can the trained agent achieve? Can the trained agent beat easy/median/hard bot in sc2 ? — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>