Technology: Facebook and CMU’s ‘superhuman’ poker AI beats human pros - PressFrom - US
  •   
  •   
  •   

TechnologyFacebook and CMU’s ‘superhuman’ poker AI beats human pros

22:00  11 july  2019
22:00  11 july  2019 Source:   theverge.com

Watch: Tiger loses poker showdown to NBA superstar in Vegas

Watch: Tiger loses poker showdown to NBA superstar in Vegas Tiger Woods was bounced from his charity Tiger Jam poker event at MGM Grand in Las Vegas by NBA superstar Russell Westbrook on an absolutely brutal beat. With an ace-king in hand, Woods went all-in against Westbrook’s queen-queen. And despite a brief moment of elation when he saw a second ace on the flop, the 15-time major winner is devastated a moment later when a third queen is revealed. Even if you’re @TigerWoods or @russwest44, you just can’t avoid those flips. #TigerJampic.twitter.

Facebook and CMU’s ‘superhuman’ poker AI beats human pros© Photo credit should read LIONEL BONAVENTURE/AFP/Getty Images

AI has definitively beaten humans at another of our favorite games. A program, designed by researchers from Facebook’s AI lab and Carnegie Mellon University, has bested some of the world’s top poker players in a series of games of six-person no-limit Texas Hold ‘em poker.

Over 12 days and 10,000 hands, the AI system named Pluribus faced off against 12 pros in two different settings. In one, the AI played alongside five human players; in the other, five versions of the AI played with one human player (the computer programs were unable to collaborate in this scenario). Pluribus won an average of $5 per hand with hourly winnings of around $1,000 — a “decisive margin of victory,” according to the researchers.

'Jeopardy!' superstar testing his gambling skills in the World Series of Poker

'Jeopardy!' superstar testing his gambling skills in the World Series of Poker Jeopardy superstar James Holzhauer may have put down the buzzer, but he's picking up his chips and heading to Las Vegas to participate in the World Series of Poker on Monday.

“It’s safe to say we’re at a superhuman level and that’s not going to change,” Noam Brown, a research scientist at Facebook AI Research and co-creator of Pluribus, told The Verge.

“we’re at a superhuman level and that’s not going to change.”

“Pluribus is a very hard opponent to play against. It’s really hard to pin him down on any kind of hand,” Chris Ferguson, a six-time World Series of Poker champion and one of the 12 pros drafted against the AI, said in a press statement.

In a paper published in Science, the scientists behind Pluribus say the victory is a significant milestone in AI research. Although machine learning has already reached superhuman levels in board games like chess and Go, and computer games like Starcraft II and Dota, six-person no-limit Texas Hold ‘em represents, by some measures, a higher benchmark of difficulty.

'Jeopardy!' champ out of World Series of Poker in Las Vegas

'Jeopardy!' champ out of World Series of Poker in Las Vegas LAS VEGAS (AP) — "Jeopardy!" champion and professional sports gambler James Holzhauer didn't have as much success in his first appearance at two World Series of Poker events in Las Vegas. Tournament spokesman Seth Palansky said Tuesday that Holzhauer and Poker Hall of Famer Mike Sexton played about five hours Monday before finishing out of the money in a tag-team tournament. That was Holzhauer's second event of the day. Earlier, the 32-time

Not only is the information needed to win hidden from players (making it what’s known as an “imperfect-information game”), it also involves multiple players and complex victory outcomes. The game of Go famously has more possible board combinations than atoms in the observable universe, making it a huge challenge for AI to map out what move to make next. But all the information is available to see, and the game only has two possible outcomes for players: win or lose. This makes it easier, in some senses, to train an AI on.

Facebook and CMU’s ‘superhuman’ poker AI beats human pros© Credit: Facebook

A timeline of Pluribus’ training regime. “Limping” is one strategy used by some human players that the AI eventually discarded.

Back in 2015, a machine learning system beat human pros at two-player Texas Hold ‘em, but upping the number of opponents to five increases the complexity significantly. To create a program capable of rising to this challenge, Brown and his colleague Tuomas Sandholm, a professor at CMU, deployed a few crucial strategies.

Would You Pay $30 a Month to Check Your Email?

Would You Pay $30 a Month to Check Your Email? The year is 2019, and the brainy engineers of Silicon Valley are hunkered down, working on transformative, next-generation technologies like self-driving cars, digital currencies and quantum computing. 

Pluribus was trained in just eight days for an estimated cost of just $150

First, they taught Pluribus to play poker by getting it to play against copies of itself — a process known as self-play. This is a common technique for AI training, with the system able to learn the game through trial and error; playing hundreds of thousands of hands against itself. This training process was also remarkably efficient: Pluribus was created in just eight days using a 64-core server equipped with less than 512GB of RAM. Training this program on cloud servers would cost just $150, making it a bargain compared to the hundred-thousand-dollar price tag for other state-of-the-art systems.

Then, to deal with the extra complexity of six players, Brown and Sandholm came up with an efficient way for the AI to look ahead in the game and decide what move to make, a mechanism known as the search function. Rather than trying to predict how its opponents would play all the way to the end of the game (a calculation that would become incredibly complex in just a few steps), Pluribus was engineered to only look two or three moves ahead. This truncated approach was the “real breakthrough,” says Brown.

Former NFL star Richard Seymour finishes impressive 5-day run at World Series of Poker

Former NFL star Richard Seymour finishes impressive 5-day run at World Series of Poker Former NFL All-Pro defensive lineman Richard Seymour gave the World Series of Poker Main Event a run for its money. But in the Super Bowl of poker tournaments, Seymour came up short of the ultimate prize when he was eliminated on Day 5 of the event in 131st place. It was an admirable showing for the three-time Super Bowl champion, who has taken up competitive poker since retiring from football. Seymour will take home $59,295 for his troubles (buy-in was $10,000), well short of the $10 million grand prize.

You might think that Pluribus is sacrificing long-term strategy for short-term gain here, but in poker, it turns out short-term incisiveness is really all you need.

“it can bluff better than any human.”

For example, Pluribus was remarkably good at bluffing its opponents, with the pros who played against it praising its “relentless consistency,” and the way it squeezed profits out of relatively thin hands. It was predictably unpredictable: a fantastic quality in a poker player.

Brown says this is only natural. We often think of bluffing as a uniquely human trait; something that relies on our ability to lie and deceive. But it’s an art that can still be reduced to mathematically optimal strategies, he says. “The AI doesn’t see bluffing as deceptive. It just sees the decision that will make it the most money in that particular situation,” he says. “What we show is that an AI can bluff, and it can bluff better than any human.”

What does it mean, then, that an AI has definitively bested humans as the world’s most popular game of poker? Well, as we’ve seen with past AI victories, humans can certainly learn from the computers. Some strategies that players are generally suspicious of (like “donk betting”) were embraced by the AI, suggesting they might be more useful than previously thought. “Whenever playing the bot, I feel like I pick up something new to incorporate into my game,” said poker pro Jimmy Chou.

AI program beats pros in six-player poker -- a first

AI program beats pros in six-player poker -- a first Artificial intelligence programs have bested humans in checkers, chess, 

There’s also the hope that the techniques used to create Pluribus will be transferrable to other situations. Many scenarios in the real world resemble Texas Hold ‘em poker in the broadest sense — meaning they involve multiple players, hidden information, and numerous win-win outcomes.

Brown and Sandholm hope that the methods they have demonstrated could therefore be applied in domains like cybersecurity, fraud prevention, and financial negotiations. “Even something like helping navigate traffic with self driving cars,” says Brown.

So can we now consider poker a “beaten” game?

Brown doesn’t answer the question directly, but he does say it’s worth noting that Pluribus is a static program. After its initial eight-day training period, the AI was never updated or upgraded so it could better match its opponents’ strategies. And over the 12 days it spent with the pro, they were never able to find a consistent weakness in its game. There was nothing to exploit. From the moment it started betting, Pluribus was on top.

Ogg cancels contract with consultant tangled in poker room busts.
Harris County District Attorney Kim Ogg has canceled a contract with a consultant accused of defrauding a private Houston poker club in a $250,000 scheme, her office said. First Assistant County Attorney Robert Soard said Ogg canceled the contract with Amir Mireskandari on Monday, the day before the district attorney dismissed charges against nine employees of two Houston members-only poker clubs She cited potential conflicts of interest, including the consultant, in announcing the dismissal of the charges. Ogg also said she had asked the FBI to investigate the cases.

—   Share news in the SOC. Networks

Topical videos:

usr: 0
This is interesting!