DeepMind, the Alphabet Inc-owned artificial intelligence (AI) company best known for creating software capable of beating the world’s best go players, has targeted StarCraft II as its next big research milestone, but so far, space is proving a difficult frontier for the company’s algorithms.
DeepMind’s algorithms, including those that performed with superhuman skill across a host of classic Atari titles, “cannot win a single game against the easiest built-in AI” in StarCraft II, let alone challenge skilled humans, the company said in a blog post on Wednesday.
The built-in agents, which are created by StarCraft publisher Activision Blizzard Inc, use hard-coded rules to determine their gameplay rather than the kinds of advanced machine learning techniques in which DeepMind specializes.
Photo: EPA
The company said new breakthroughs in machine learning would be required for its software agents to master the game.
The post did not reveal how close DeepMind might be to such breakthroughs.
The algorithm that mastered the Atari games was unveiled in June last year. Since then, DeepMind has published a number of research papers that hint it might be closing in on creating software capable of many of the tasks — such as prioritizing goals, long-term planning and memory — that any system would need to play StarCraft II successfully.
The company said that its algorithms performed well at learning some basic steps, such as moving around the game environment and selecting units, that would be critical to mastering the game.
StarCraft is considered an important target for machine-learning researchers because, unlike go, in which both players can see the entire board and take turns moving pieces, players in StarCraft cannot see what is happening in the entire game environment at one time and both players move their units simultaneously.
The game also requires players to carry out sub-tasks, such as building structures and mining resources, while also conducting reconnaissance, mounting attacks and defending territory.
To succeed, a player needs to have a good memory, prioritize among tasks and plan under conditions of uncertainty.
Because of these factors, StarCraft II comes much closer to approximating many real-world situations than games such as chess, go or even poker.
StarCraft II is also used in e-sports competitions, so there are highly skilled human opponents with which an AI can match wits.
To help computer scientists use StarCraft II as a testbed for AI, DeepMind has partnered with Blizzard to create an interface that allows outside software to access and play the game.
The two companies this week unveiled the interface, along with a set of tools to help other computer scientists train AI agents to play the game, at a machine learning conference in Australia.
Among the tools Blizzard is making public are a dataset of anonymized game replays — recordings of humans playing the game — that computer scientist would be able to use to help train their systems.
“One technique that we know allows our agents to learn stronger policies is imitation learning,” DeepMind said in its blog post. “This kind of training will soon be far easier thanks to Blizzard, which has committed to ongoing releases of hundreds of thousands of anonymized replays.”
DeepMind also said it was releasing a series of “mini-game” environments that would help researchers train their AI agents on basic components of the game.
It follows efforts by other companies, such as Facebook Inc and Microsoft Corp, to open game environments, including the original StarCraft and Minecraft, to the entire AI research community.
PRICE HIKES: The war in the Middle East would not significantly disrupt supply in the short term, but semiconductor companies are facing price surges for materials Taiwan’s semiconductor companies are not facing imminent supply disruptions of essential chemicals or raw materials due to the war in the Middle East, but surges in material costs loom large, industry association SEMI Taiwan said yesterday. The association’s comments came amid growing concerns that supplies of helium and other key raw materials used in semiconductor production could become a choke point after Qatar shut down its liquefied natural gas (LNG) production and helium output earlier this month due to the conflict. Qatar is the second-largest LNG supplier in the world and accounts for about 33 percent of global helium output. Helium is
DOMESTIC COMPONENT: Huang identified several Taiwanese partners to be a key part of Nvidia’s Vera Rubin supply chain, including Asustek, Hon Hai and Wistron Nvidia Corp chief executive officer Jensen Huang (黃仁勳), addressing crowds at the company’s biggest annual event, unveiled a variety of new products while predicting that its flagship artificial intelligence (AI) processors would help generate US$1 trillion in sales through next year. During a two-and-a-half-hour keynote address, Huang announced plans to push deeper into central processing units (CPUs) — Intel Corp’s home turf — and introduced semiconductors made with technology acquired from start-up Groq Inc. The company even said it was developing chips for data centers in outer space. At the heart of Huang’s speech was the message that demand for computing power
OPTIMISTIC: Inflation still has a chance of remaining below the central bank’s 2 percent alert level, as Taiwan’s economy is resilient with healthy exports, the NDC minister said Taiwan’s inflation could exceed 2 percent this year if oil prices continue to surge amid escalating tensions in the Middle East, prompting the government to reassess its economic outlook, the Directorate-General of Budget, Accounting and Statistics (DGBAS) said yesterday. DGBAS Minister Chen Shu-tzu (陳淑姿) told lawmakers at a meeting of the legislature’s Finance Committee that the agency’s earlier growth forecast of 1.68 percent in the consumer price index (CPI) and 7.71 percent for GDP this year did not account for the ongoing Middle East conflict and would need revision, if tensions persist. The previous forecast assumed an average international crude price of
ELECTRIC DREAMS: Smart cities would use ‘virtual power plants,’ which integrate idle electricity use from households, businesses and factories, Asustek said Asustek Computer Inc (華碩) yesterday showcased key components of its artificial intelligence (AI)-driven smart city initiatives at a trade show in Taipei, eyeing new business opportunities as cities develop sovereign AI infrastructure. Advances in generative, multimodal and physical AI are driving cities toward a new phase of “sovereign AI,” Asustek cochief executive officer Samson Hu (胡書賓) told reporters on the sidelines of the Smart City Summit and Expo at Taipei Nangang Exhibition Center’s Hall 2. The company showcased its “AI City” framework, which comprises three layers — computing infrastructure centered on AI servers, AI models and a platform layer for data processing
RSS