An Overdue Post on AlphaStar, Part 1
So, i almost ALWAYS play protoss 1v1. My knowledge of weaknesses (not going to go past tier 2): vs zealots: stalkers/sentries win.come kenja no mago 5 raw the best of jenna haze lojra per femije me makina
AlphaStar won 10 of its 11 matches against pro players. The previous matches were an impressive display of AI prowess. AlphaStar understood resource allocation, cover, and unit micromanagement better than most human players. Naturally, its ability to seamlessly control multiple units also helped. Sadly, there is no way to ensure you get to play a match against AlphaStar. Blizzard will let DeepMind run several different agents on Battle. DeepMind is primarily interested in testing AlphaStar in matches where players vary their strategies, and keeping the matching secret ensures a controlled test.
Log In Log In Register. StarCraft 2 Brood War Blogs. News Featured News. StarCraft 2 General. Brood War General. Other Games Heroes of the Storm. LoL Tournaments.
StarCraft 2 Protoss Build Orders and Guides
The Colossi-Push is a powerful All-In. It will be played on two fully saturated bases. You can even win over experienced Terran players with this build. Hier gibt es eine einfache Variante. In order to enhance our production as a Zerg we need more Larvae and therefore more Hatcheries. During this practice build we construct a second Hatchery early in the game and commence a Speedling attack. Mit diesem All-In lernt ihr eine sichere Variante kennen, um im PvP zu expandieren und setzt einen gezielten Push, mit dem ihr das Spiel beendet.
This made waves in both the StarCraft and machine learning communities. As such, this is a two-part post. The second part, linked here , is a more detailed discussion of what AlphaStar means for machine learning. It was always a matter of time. No one knew OpenAI was looking at DotA 2, until they announced they had beaten a top player in 1v1 with conditions. It was on the horizon if you saw the right signs see my post on AlphaGo if curious.