Facebook's artificial intelligence-powered machine defeats FIVE Texas hold'em champions at once 

A computer has beaten five of the world’s champion players at poker — a game once thought too difficult for machines to master.

It is the latest milestone marking the superior powers of machines over people and the first time a computer has beaten more than one opponent in a complex game of strategy and calculation.

Computers first defeated the human world champion at chess in 1996 — and the even-more complex Chinese strategy game of Go two years ago.

But poker has posed a tougher challenge as it involves several players around the table.

And unlike in chess or Go, the computer does not have access to all the information available as it cannot see its opponent’s cards.

So it has to guess if a human player is bluffing — pretending to hold a better hand than it does.

Scroll down for video 

A computer has beaten five of the world’s champion players at poker — a game once thought too difficult for machines to master

Not only did it call its opponent’s bluff, it was brilliant at bluffing itself.

It was also able to keep its rivals guessing – playing wildly at times and conservatively at others.

The human poker aces it crushed included Darren Elias, record-holder of most World Poker Tour titles, and Chris ‘Jesus’ Ferguson, winner of six World Series of Poker events.

Each pro separately played 5,000 hands of poker against five copies of Pluribus, developed at Carnegie Mellon University in the US in collaboration with Facebook.

In another experiment involving 13 pros, all of whom have won more than one million US dollars playing poker, Pluribus played five pros at a time for a total of 10,000 hands and again emerged victorious.

Its developer Professor Tuomas Sandholm, of Carnegie Mellon University in the US, has said: ‘Pluribus achieved superhuman performance at multi-player poker, which is a recognised milestone in artificial intelligence and in game theory that has been open for decades.’

‘Thus far, superhuman AI milestones in strategic reasoning have been limited to two-party competition.’

The human poker aces it crushed included Darren Elias (pictured), record-holder of most World Poker Tour titles, and Chris ‘Jesus’ Ferguson, winner of six World Series of Poker events

‘The ability to beat five other players in such a complicated game opens up new opportunities to use AI to solve a wide variety of real-world problems.’ 

The computer developed its winning strategy by playing thousands of games against itself.

Its developer, Tuomas Sandholm of Carnegie Mellon University in the US, is pictured

It then adopted the winning approach each time.

Its makers said Pluribus has learnt to be unpredictable.

If it only made large bets when holding very good hands, its opponents will quickly catch on, and quickly throw in their cards.

So Pluribus has learnt to keep its rivals guessing.

Research co-author Noam Brown, of Facebook AI said: ‘We’re elated with its performance and believe some of Pluribus’ playing strategies might even change the way pros play the game.’ 

Poker pro Mr Elias said: ‘Its major strength is its ability to use mixed strategies.’

‘That’s the same thing that humans try to do. It’s a matter of execution for humans – to do this in a perfectly random way and to do so consistently. Most people just can’t.’ 

Pluribus registered a solid win, and Mr Elias said ‘The bot wasn’t just playing against some middle of the road pros. It was playing some of the best players in the world.’ 

HOW DOES ARTIFICIAL INTELLIGENCE LEARN?

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn.

ANNs can be trained to recognise patterns in information – including speech, text data, or visual images – and are the basis for a large number of the developments in AI over recent years.

Conventional AI uses input to ‘teach’ an algorithm about a particular subject by feeding it massive amounts of information.   

AI systems rely on artificial neural networks (ANNs), which try to simulate the way the brain works in order to learn. ANNs can be trained to recognise patterns in information – including speech, text data, or visual images

Practical applications include Google’s language translation services, Facebook’s facial recognition software and Snapchat’s image altering live filters.

The process of inputting this data can be extremely time consuming, and is limited to one type of knowledge. 

A new breed of ANNs called Adversarial Neural Networks pits the wits of two AI bots against each other, which allows them to learn from each other. 

This approach is designed to speed up the process of learning, as well as refining the output created by AI systems.