Pluribus is the world’s most evolved Poker AI developed by Carnegie Mellon University and Facebook AI research scientists. Here is how the software succumbed to the world’s poker elite.
Enter Pluribus,First Among the Poker AI
It’sa classic case of man against the machine. Well, if it’s anyconsolation, there originally werea fewmore men than machines, but now that Pluribusis up and running, the AI is capable of taking on as many as 5 pokeropponents at the same table. Developed by Carnegie MellonUniversity and FacebookAI scientists, as many as 15professional poker players took on the software to find themselvesall defeated in No-Limit Texas Hold’em.
Pluribusfirst took on Chris “Jesus” Ferguson,a player who has won the highest distinction in poker by topping theWorld Series of Poker six times. Darren Elias,meanwhile, lost, despite the fact that he holds the most poker titlesin the world.
Facebook AI and @CarnegieMellon researchers have built Pluribus, the first AI bot to beat elite poker pros in 6 player Texas Hold’em. This breakthrough is the first major benchmark outside of 2 player games and we’re sharing specifics on how we built it. https://t.co/zId9x4VBqc pic.twitter.com/u89irNcxEK
— Facebook AI (@facebookai) July 11, 2019
Inthe first match-up, five copies of the AI were set against the proswith over 5,000 handsplayed each time.When Pluribus took on all five players, 10,000 were played. Whilesome may think that machines would logically have the upper hand,Tuomas Sandholm whoco-authored the project at Carnegie Mellon University, begged todiffer.
Accordingto M. Sandholm, who took 16 years to tackle poker by teaching an AIhow to play and defeat the world’s elite, poker is agame with imperfect information wherethere are many unknowns. Misleading information is proffered readilyand an AI is really no good judge of character. It can only tell youprobabilities.
Riseof the Machines: From Claudico to Libratus, to Pluribus
The evolution of AI has been somewhat quicker than your average species development. Sandholm’s team has been trying to create the ultimate poker-playing machine for 16 years, and to this end alone, much testing was needed.
After years of research, a predecessor of the AI, Claudico, was fielded at the Brains vs. Artificial Intelligence tournament held in the Rivers Casino in Pittsburgh. Claudico played through 80,000 hands in the course of two weeks, but he fell short of achieving a convincing victory, which judges said could have been thanks to luck.
Emboldenedby their efforts, the team went back to the table and gave Claudico anew purpose – to improve its own game rather than try and home inon the mistakes of others. Thus, Libratuswas born. This new AI was designed to be much more assertive as well.Researchers also saw merit in increasing the number of hands thecomputer played, so 120,000 hands were assigned.
Libratus was in a much better form than his sibling and it also proved a powerful AI that knew when to bluff and when to play. The AI took on four players and played 120,000 combined hands of poker, winning by $1.7 million and achieving the statistical significance that promoted the AI as the clear winner.
Itis important to note that at this time, Libratus was taking on singleopponents, rather than being challenged by several different playersat the same time. That meant more work for Sandholm and his team whowere glad to go back to improving the AI.
Libratus was superior to Pluribus,but it also shared similarities. For example, Libratus didn’t try tomemorize strategies, but it rather useda strategy that manyof today’s professionals would agree is what makes a great player,i.e. being unpredictable.
The objective was clear: devise a way for the AI to follow through with all the different moves players do. To do this, Sandholm’s team had to develop basic behavioral rules, which while intended to limit the possible outcomes, amounted to as many as “six million continuation strategies”, as the researcher noted himself.
WhatLibratus did was to go back four moves for every player move and tryto reason why they would play the way they did.
Libratuswas superior to Pluribus, but it also shared similarities. Forexample, Libratus didn’t try to memorize strategies,but it rather useda strategy that manyof today’s professionals would agree is what makes a great player,i.e. being unpredictable.
Libratuswas smart enough to devise its own strategies by training againstitself and experiencing new situations from which it could learn.Uniquely, the AI taught itself to be random out of its own accordrather than being programmed to devise randomized strategies.
SoakingUp the AI Wisdom: Play Only When You Are Sure
And so we arrive atPluribus, the most advanced version of the AI capable of taking onmultiple opponents at the same time and playing against multipleplayers at the same table. If there is one immediate observation thatresearchers made while watching Pluribus play, it was that the AIdidn’t engage in empty hands. It either raised or folded, rather thancalling.
Conversely, a part of the strange strategies of the AI included the so-called practice of donk betting whereby the AI purposefully called one hand but raised the one right after it. In fact, Pluribus was doing this way too often – more often than a human player.
The true strengthof the AI lg777 , however, lied in the fact that it achieved completerandomization of its strategies. It didn’t follow any patterns andplayed with bet sizes that varied all the time, introducingadditional confusion among the players. The AI’s behaviordemonstrateda level of play that hasn’t yet been mastered by humans. Here is whatpoker player Michael Gaglianohad to say:
“Therewere several plays that humans simply are not making at all,especially relating to its bet sizing. Bots/AI are an important partin the evolution of poker, and it was amazing to have first-handexperience in this large step toward the future.”
Meanwhile, the Sandholm team is already looking into real-world applications for their software. Pluribus, true to its name, could be used to research new drugs and address pressing health issues, such as antibiotic-resistant bacteria. Yet, Sandholm’s team has licensed the AI to companies that work on defense and intelligence and gaming and entertainment.
How Are Bots Going to Impact the Community?
The success of Pluribus has been welcomed but it has also made people question the future of the game. Would such AI be leveraged by teams that send a poker player and then communicate the best strategies with him? According to the team, you could develop a similar AI on a $150 cloud service. However, the security at the live tournament is too good to allow it, but the fact that Pluribus needs some 12,000 playing hours and only 28 cores to p out how to play is disconcerting
Yet, it’s unlikely to mess with the poker community. For starters, the team behind the project isn’t releasing the code, cognizant of the havoc it could cause. There have been similar qualms about AI in other verticals, including competitive video gaming where an AI taught itself how to beat the world’s elite in StarCraft II.
