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.
Taiwan’s long-term economic competitiveness will hinge not only on national champions like Taiwan Semiconductor Manufacturing Co. (TSMC, 台積電) but also on the widespread adoption of artificial intelligence (AI) and other emerging technologies, a US-based scholar has said. At a lecture in Taipei on Tuesday, Jeffrey Ding, assistant professor of political science at the George Washington University and author of "Technology and the Rise of Great Powers," argued that historical experience shows that general-purpose technologies (GPTs) — such as electricity, computers and now AI — shape long-term economic advantages through their diffusion across the broader economy. "What really matters is not who pioneers
In a high-security Shenzhen laboratory, Chinese scientists have built what Washington has spent years trying to prevent: a prototype of a machine capable of producing the cutting-edge semiconductor chips that power artificial intelligence (AI), smartphones and weapons central to Western military dominance, Reuters has learned. Completed early this year and undergoing testing, the prototype fills nearly an entire factory floor. It was built by a team of former engineers from Dutch semiconductor giant ASML who reverse-engineered the company’s extreme ultraviolet lithography (EUV) machines, according to two people with knowledge of the project. EUV machines sit at the heart of a technological Cold
Taiwan Semiconductor Manufacturing Co (TSMC, 台積電) last week recorded an increase in the number of shareholders to the highest in almost eight months, despite its share price falling 3.38 percent from the previous week, Taiwan Stock Exchange data released on Saturday showed. As of Friday, TSMC had 1.88 million shareholders, the most since the week of April 25 and an increase of 31,870 from the previous week, the data showed. The number of shareholders jumped despite a drop of NT$50 (US$1.59), or 3.38 percent, in TSMC’s share price from a week earlier to NT$1,430, as investors took profits from their earlier gains
TAIWAN VALUE CHAIN: Foxtron is to fully own Luxgen following the transaction and it plans to launch a new electric model, the Foxtron Bria, in Taiwan next year Yulon Motor Co (裕隆汽車) yesterday said that its board of directors approved the disposal of its electric vehicle (EV) unit, Luxgen Motor Co (納智捷汽車), to Foxtron Vehicle Technologies Co (鴻華先進) for NT$787.6 million (US$24.98 million). Foxtron, a half-half joint venture between Yulon affiliate Hua-Chuang Automobile Information Technical Center Co (華創車電) and Hon Hai Precision Industry Co (鴻海精密), expects to wrap up the deal in the first quarter of next year. Foxtron would fully own Luxgen following the transaction, including five car distributing companies, outlets and all employees. The deal is subject to the approval of the Fair Trade Commission, Foxtron said. “Foxtron will be
RSS