Groups Similar Look up By Text Browse About



Similar articles
Article Id Title Prob Score Similar Compare
143039 THEVERGE 2019-7-11:
Facebook and CMU’s ‘superhuman’ poker AI beats human pros
1.000 Find similar Compare side-by-side
142924 TECHCRUNCH 2019-7-11:
AI smokes 5 poker champs at a time in no-limit Hold’em with ‘relentless consistency’
0.980 0.682 Find similar Compare side-by-side
143037 VENTUREBEAT 2019-7-11:
Facebook’s AI beats human poker champions
0.990 0.675 Find similar Compare side-by-side
142999 ARSTECHNICA 2019-7-11:
Facebook AI Pluribus defeats top poker professionals in 6-player Texas Hold ’em
0.991 0.672 Find similar Compare side-by-side
143004 ENGADGET 2019-7-11:
Facebook and CMU's poker AI beat five pros at once
0.994 0.641 Find similar Compare side-by-side
142995 ARSTECHNICA 2019-7-11:
DeepMind AI is secretly lurking on the public StarCraft II 1v1 ladder
0.019 0.534 Find similar Compare side-by-side
142974 ENGADGET 2019-7-11:
DeepMind's ‘Starcraft II’ AI will play public matches
0.024 0.523 Find similar Compare side-by-side
143351 VENTUREBEAT 2019-7-15:
How video game engines help create smarter AI
0.467 Find similar Compare side-by-side
142436 VENTUREBEAT 2019-7-8:
The AI for Good nominees for the Transform AI Innovation Awards
0.435 Find similar Compare side-by-side
142922 VENTUREBEAT 2019-7-11:
Facebook VP: AI has a compute dependency problem
0.132 0.418 Find similar Compare side-by-side
143226 VENTUREBEAT 2019-7-12:
AI Weekly: Highlights from VentureBeat’s AI conference Transform
0.004 0.414 Find similar Compare side-by-side
142767 VENTUREBEAT 2019-7-10:
OpenAI: Explainability and reasoning should inform future AI models
0.401 Find similar Compare side-by-side
143102 VENTUREBEAT 2019-7-11:
AWS AI VP: Developers drive all innovation in technology
0.395 Find similar Compare side-by-side
142709 THEVERGE 2019-7-9:
Apex Legends’ ranked mode will be the key to keeping it alive
0.393 Find similar Compare side-by-side
142559 VENTUREBEAT 2019-7-9:
The Startup Spotlight nominees for the Transform AI Innovation Awards
0.382 Find similar Compare side-by-side
142914 VENTUREBEAT 2019-7-11:
Announcing the AI Innovation Awards winners at Transform 2019
0.381 Find similar Compare side-by-side
143123 VENTUREBEAT 2019-7-12:
To be successful with AI, you have to start small
0.004 0.377 Find similar Compare side-by-side
142462 THEVERGE 2019-7-8:
Dr. Mario World feels more like Candy Crush than the classic NES game
0.367 Find similar Compare side-by-side
142986 ARSTECHNICA 2019-7-11:
Steam uses machine learning for its new game recommendation engine
0.364 Find similar Compare side-by-side
142940 TECHCRUNCH 2019-7-11:
There’s a tennis game hidden in Google right now; here’s how to find it
0.362 Find similar Compare side-by-side
143125 ARSTECHNICA 2019-7-12:
Want to be more creative? Playing Minecraft can help, new study finds
0.362 Find similar Compare side-by-side
143074 VENTUREBEAT 2019-7-10:
Kayak: AI isn’t a ‘wonder weapon’ that will solve all your problems
0.358 Find similar Compare side-by-side
143009 VENTUREBEAT 2019-7-11:
Call of Duty: Modern Warfare will have 2 vs. 2 Gunfight multiplayer mode
0.349 Find similar Compare side-by-side
143129 VENTUREBEAT 2019-7-12:
Cloudera’s Hilary Mason on how businesses can avoid ruining their own AI projects
0.348 Find similar Compare side-by-side
143248 TECHCRUNCH 2019-7-12:
Elon Musk-backed Neuralink to detail its progress on upgrading the brain to keep pace with AI
0.347 Find similar Compare side-by-side

1

ID: 143039

URL: https://www.theverge.com/2019/7/11/20690078/ai-poker-pluribus-facebook-cmu-texas-hold-em-six-player-no-limit

Date: 2019-07-11

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

AI has definitively beaten humans at another of our favorite games. A program, designed by researchers from Facebooks AI lab and Carnegie Mellon University, has bested some of the worlds 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. Its safe to say were at a superhuman level and thats not going to change, Noam Brown, a research scientist at Facebook AI Research and co-creator of Pluribus, told The Verge. Pluribus is a very hard opponent to play against. Its 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. Not only is the information needed to win hidden from players (making it whats 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. 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. 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. 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. 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 its an art that can still be reduced to mathematically optimal strategies, he says. The AI doesnt 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 worlds most popular game of poker? Well, as weve 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. Theres 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 doesnt answer the question directly, but he does say its 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.