Google's DeepMind AI and Blizzard have just released the tools to let AI researchers create bots capable of competing against humans in StarCraft II. They are also opening a cache of data from 65,000 past StarCraft II games, and they say the trove will grow by around half a million games each month. Late Monday, Facebook released its own collection of data from 65,000 human-on-human games of the original StarCraft to help bot builders.
I can certainly see how StarCraft would be several orders of magnitude harder for an AI than the games that they have been dominating at prior. The article states that they are estimating five years before a StarCraft bot can beat a human. A question I have though, is why does Facebook have the data from 65,000 StarCraft games?!
In chess and Go, you can see all your opponent’s moves and pieces, making them so-called perfect information games. StarCraft is an imperfect information game. You cannot see all of your opponents’ troop deployments or construction projects, forcing you to use what you’ve seen, and your mental model of the game, to predict what they may be planning.
I can certainly see how StarCraft would be several orders of magnitude harder for an AI than the games that they have been dominating at prior. The article states that they are estimating five years before a StarCraft bot can beat a human. A question I have though, is why does Facebook have the data from 65,000 StarCraft games?!
In chess and Go, you can see all your opponent’s moves and pieces, making them so-called perfect information games. StarCraft is an imperfect information game. You cannot see all of your opponents’ troop deployments or construction projects, forcing you to use what you’ve seen, and your mental model of the game, to predict what they may be planning.