Summary #900

AlphaStar: Grandmaster level in StarCraft II using multi-agent reinforcement learning

deepmind.com
  • AI agent AlphaStar has been trained, using novel techniques, to be better than 99.8% Starcraft II players, and achieve Grandmaster level for all 3 races in the game.
  • The AI uses a camera interface, it’s limited to receiving similar input information, and playing at a similar speed to human players, and plays anonymously on Battle.net.
  • One of the key innovations was using a League self-play system, which involved flaw-exposing agents alongside win-oriented agents.
  • Other techniques included neural networks, multi-agent learning and imitation learning.
  • The study helped improve those methods by adapting them to a complex, dynamic environment, contributing to the safety and robustness of AI systems in general.

Categories

  • Science Science (59) Study shows, for the first time, that giving Oxytocin to men with autism can have lasting positive effects
  • Psychology Psychology (64) You’re more likely to make a decision when you breathe out
  • Cosmos Cosmos (29) Astronomers witness the dragging of space-time in stellar cosmic dance
  • History History (14) Humans survived off rodents in the mountains during the last ice age, study says
  • Society Society (65) The start-up bubble is finally bursting (a little bit)
  • Medicine Medicine (65) Scientists discover powerful antibiotic using AI
  • Technology Technology (70) Polymer patch could reduce negative effects of cardiac scar tissue
  • Nature Nature (45) Scientists are trying to save bees with special bacteria for bee gut microbiome

Newsletter

Newsletter

Fame 🙌

Bullets.tech - Articles for science lovers shortened to five bullet points. | Product Hunt Embed

We were featured on Hacker News, O'REILLY® Ideas, and Boing Boing.