Reinforcement Learning with AWS DeepRacer

In March 2016, Lee Sedol, the greatest Go player of the past decade, was defeated 4–1 by <a href="https://deepmind.com/research/case-studies/alphago-the-story-so-far" rel="noopener ugc nofollow" target="_blank">AlphaGo</a>. Computers have beaten the best humans at chess before, but Go is at another next level at complexity. Do you know what’s even crazier? The machine had only been learning how to play for the past 8 hours before the match. This January 2019, the Google DeepMind team took AlphaGo to another level, making <a href="https://deepmind.com/blog/article/alphastar-mastering-real-time-strategy-game-starcraft-ii" rel="noopener ugc nofollow" target="_blank">AlphaStar</a>. Starcraft is one of the most complex video games out there and it’s never been mastered by a computer  before, until now. AlphaStar took out two world-class players, beating them both 5–0. <a href="https://towardsdatascience.com/reinforcement-learning-with-aws-deepracer-99b5dd2557c8">Learn More</a>