StarAi: Deep Reinforcement Learning Course
4 comments
Great! I would argue that no, there's still no great resource to learn RL "from scratch" - there's still a huge gap between Sutton&Barto and implementing DDPG. You have to figure out everything by reading existing implementations, various Medium posts (a lot of them containing errors and imprecisions), and research papers. I wouldn't consider Spinning Up as a beginner-friendly resource, it's too dense/math-heavy
The closest I have found so far is the Udacity course: https://eu.udacity.com/course/deep-reinforcement-learning-na... which costs $1000
So yeah, I'm excited to see what you've done! I'm working on a similar course, FYI.
The closest I have found so far is the Udacity course: https://eu.udacity.com/course/deep-reinforcement-learning-na... which costs $1000
So yeah, I'm excited to see what you've done! I'm working on a similar course, FYI.
When I first started with RL I went through David Silver's course. I still think it's my favorite set of materials aside from "Artificial Intelligence: A modern approach by Russell and Norvig" https://www.youtube.com/playlist?list=PLbWDNovNB5mqFBgq7i3MY...
I also think OpenAi's spinning up isn't beginner friendly.
Thank you for this.
Going to start this weekend.
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/
.