Reinforcement learning algorithms and architecture behind Alphastar AI

  • Thursday, March 19th 2020, 18:30 - 20:30
  • Online

In 2018, Deepmind unveiled Alphastar, one of most advanced AI capable to defeat top professional players in Starcraft.

Starcraft real-time strategy game was long time considered a grand challenge for #AI due to large action space, imperfect state information and no single superior strategy available. The game requires to constantly balance the short and long-term goals and adapt to unexpected situations.

Alex Movila, Software Engineer at Fortech, passionate about deep learning will guide us in the architecture and some of the reinforcement algorithms used by Alphastar.

Meet the speaker

Alex Movilă
Alex Movilă Senior Java developer at Fortech

Since 2001, Alex has worked as a Java developer for several companies (Iași and Netherlands) and in the recent years he became passionate about deep learning.