【TV Series Archives】

Google's DeepMind lab has built an artificially intelligent program that taught itselfto become one of the world's most dominant Go players. Google says the program,TV Series Archives AlphaGo Zero, endowed itself with "superhuman abilities," learning strategies previously unknown to humans.

AlphaGo Zero started out with no clue how to win the game Go -- a 2,500-year old Chinese game in which two players use black and white tiles to capture more territory than their opponents.

SEE ALSO: A computer beat a champion of the strategy game Go for the first time

It took AlphaGo Zero just three days to beat an earlier AI program (AlphaGo Lee), which had resoundingly beaten world champion Lee Sedol in 2016. After 21 days of playing, AlphaGo Zero defeated AlphaGo Master, an intelligent program known for beating 60 top pros online and another world champion player in 2017. By day 40, AlphaGo Zero had defeated all previous AI versions of AlphaGo.

And it achieved all these victories without any human-provided strategies or game-playing knowledge. Google published their results this week in the journal Nature.

"The most important idea in AlphaGo Zero is that it learns completely tabula rasa— that means it starts from a blank slate and figures out for itself, only from self-play, without any human knowledge, any human data, without any human examples or features or intervention from humans," said lead AlphaGo researcher David Silver in a Natureinterview.

After watching their machine learn human strategies, Silver and his team watched AlphaGo Zero autonomously attain superhuman abilities.

Mashable Light Speed Want more out-of-this world tech, space and science stories? Sign up for Mashable's weekly Light Speed newsletter. By clicking Sign Me Up, you confirm you are 16+ and agree to our Terms of Use and Privacy Policy. Thanks for signing up!

"So what we started to see is that AlphaGo Zero not only discovered the common pattern and openings that humans tend to play... it also learned them, discovered them, and ultimately discarded them in preference for its own variance which humans don’t even know about or play at the moment," explained Silver.

In May 2017, professional Chinese Go player Ke Jie (left)  plays against Google's artificial intelligence program AlphaGo. Credit: VCG via Getty Images

Google's researchers used a "reinforcement learning" scheme to make AlphaGo Zero intelligent enough to learn on its own. Using a deep neural network — which is an artificial model of how human minds relate ideas and make the best possible outcome predictions — AlphaGo Zero made its own expert predictions and then learned from its errors.

Over the course of some 30 million games, AlphaGo Zero made an immense number of moves. This required around $25 million in computer hardware, according to Google DeepMind chief executive Demis Hassabis.

Now that AlphaGo Zero has dominated its world competition, Google thinks this unprecedented self-learning ability can be applied to other problems, without having to spend time and resources teaching the machine.

"If you can achieve tabula rasalearning, you really have an agent that can be transplanted from the game of Go to any other domain. You untie yourself from the specifics of the domain you’re in and you come up with an algorithm that is so general that it can be applied anywhere," said Silver.

If the AlphaGo experiments are any clue, this sort of AI innovation could lead to "superhuman" thought being applied to other realms of existence — perhaps medicine or self-driving cars.

But according to DeepMind's Silver, the aim is not to outpace humans; it's for these intelligent machines to contribute to the sum of human knowledge.

"For us, the idea of AlphaGo is not to go out and defeat humans, but... for a program to be able to learn for itself what knowledge is," he said.

---

Featured Video For You

---

These AI learn by competing against each other, and it looks ridiculous

---

Topics Artificial Intelligence Google

• Shopping
• Digital Culture
• Tech
• Deals
• Science
• Social Good
• Life
• Games

• The World Wide Web Turns 30: A Timeline
• MoonPie Twitter has evolved to making dad jokes
• Olympians from North and South Korea are taking selfies together
• Apple upgrades iPad mini with completely new design and larger, 8.3
• ‘Jurassic World’: What was the headbutting dinosaur who saved the day?
• 'Scenes from a Marriage' is a raw, if predictable, performance powerhouse
• How to use iOS message effects on your iPhone
• Dad comes up with the ultimate life hack for clipping his dog's nails
• Better Buy: Previous
• How to free up storage on iPhone

• China and EU resume negotiations on EV duties following Trump tariff hikes · TechNode
• Chinese boba tea chain Chagee files for US IPO, reports rapid expansion · TechNode
• Ant Group cuts AI costs by 20% using Chinese chips · TechNode
• Microsoft denies shutting down operations in China · TechNode
• Alibaba launches and open
• Tencent tests Yuanbao AI assistant within WeChat, expanding its role beyond chat · TechNode
• Tencent upgrades Yuanbao AI with self
• Xpeng Motors to invest $413 million in flying cars this year: CEO · TechNode
• Zeekr debuts first hybrid SUV to compete with Rolls
• Chinese action game WUCHANG: Fallen Feathers opens pre

• What is Vcore and How Does It Help with Overclocking?
• The truly insidious 'WandaVision' bop picked up a well
• How to set a song as your ringtone on iPhone
• How to create an audio version of any too
• Amazon Spring Sale 2025: Best Apple AirPods 4 with ANC deal
• "WarioWare: Get It Together!" is more of a toy than a game: Review
• Indian movie 'Pad Man' tells a true story to fight menstrual stigma
• Malaysian newspaper criticised for its 'how to spot a gay person' list
• NYT Strands hints, answers for May 5
• Chloe Kim, 17, wins gold at Winter Olympics despite being 'hangry'

• EPA's leader is open to reconsidering crucial climate assessment
• Tinder users are changing their locations to match with athletes at the Winter Olympics
• The Variable Balans vs. the Tic Toc Chair: Which weird chair to try?
• Why you should stop laughing at Trump over a stock market correction
• The Bose QuietComfort Ultra headphones are on sale for $100 off
• How to follow the Olympics on Twitter
• The truly insidious 'WandaVision' bop picked up a well
• How to follow the Olympics on Twitter
• Bargaining For the Common Good
• Trump just defended Rob Porter again and it is extremely problematic