StarAi: Deep Reinforcement Learning Course

Way back in 2017 when Deepmind released their PySC2 interface - we thought it would be a fantastic opportunity to create a competition to help accelerate the current state of the art in ML.

We thought that such a competition would need a big $ prize pool in order to attract talent to try help solve the "Starcraft problem". We tried to copy the model of the original Xprize and use insurance bonds to try finance the $ prize purse. This document, literally bounced around to insurance brokers all around the world- but we got no takers :). Lucky for us - as we all know by now Deepmind more or less solved the Starcraft problem this year.

One thing we realised, early circa 2018 is that there were no bringing RL down to earth courses out there to help people get involved in the envisioned Starcraft competition. So we went ahead and made it ourselves :)

I know that other great resources such as OpenAi's spinning up have come out since then, but we would like to present our work and open source it to the community. We hope this content inspires someone out there to do great things!

https://www.starai.io/

.