This time, the company’s getting a helping hand from Blizzard, the developer behind StarCraft (as well as World of Warcraft, Hearthstone, and Overwatch), and that help will filter down to any other AI researcher who wants to take on the same challenge. In StarCraft II, as in Go, DeepMind wants to focus on machine learning, designing an AI that can teach itself to play the game. But that bot was a simple scripted system, with each rule it followed lain down by hand, similar to how the best AIs played Go before DeepMind came along. In 2010, while an undergrad at UC Berkeley, he built an AI agent which could play the first game in the series better than any of the built-in AIs. Vinyals has long experience with StarCraft. That also helps ensure the AI doesn’t waste processing power making thousands of minor decisions a minute, and focuses it on the key points. As a result, DeepMind will be capping the AI at what research scientist Oriol Vinyals describes as “high-level human” speed. Lacking fingers, muscles, or the possibility of tendonitis, an AI can naturally outclick a human player, which could result in it winning not through strategic thinking but simply by reacting quicker. One stat that top StarCraft players are ranked on is “actions per minute” (APM): essentially, the amount of times they click each minute. The AI does have some innate advantages, however. “An agent that can play StarCraft will need to demonstrate effective use of memory, an ability to plan over a long time, and the capacity to adapt plans based on new information.” And this is a real-time strategy game - both players are playing simultaneously, so every decision needs to be computed quickly and efficiently. “This makes for an even more complex challenge as the environment becomes partially observable - an interesting contrast to perfect information games such as Chess or Go. “Players must send units to scout unseen areas in order to gain information about their opponent, and then remember that information over a long period of time,” DeepMind says in a blogpost. But they can only see the area directly around units, since the rest of the map is hidden in a “fog of war”. Each player begins on opposite sides of a map, where they are tasked with building a base, training soldiers, and taking out their opponent. Most importantly, StarCraft II is a game full of hidden information. Not only do the game’s best players easily beat the top AI opponents, but it also introduces new domains for the DeepMind team to explore. One of the most popular eSports in the world, StarCraft II meets many of the requirements for an interesting challenge for DeepMind to take on.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |