SL Training Results?

[John Rachwan]

Hello,

Great job on this repo! I was wondering if you have any results of the model against bots? Such as winrate for example or sample replays.

Thanks!

[liuruoze]

Hi, thank you very much for your attention.

We have done some experiments based on mini-AlphaStar, such as first using supervised learning to train, and then using reinforcement learning to continue training. The relevant training results have been summarized in a future work to be published. When the review results come out, we will update the information immediately.

[John Rachwan]

Thank you!