Pluribus (poker bot)

Last updated

Pluribus is a computer poker player using artificial intelligence built by Facebook's AI Lab and Carnegie Mellon University. Pluribus plays the poker variation no-limit Texas hold 'em and is "the first bot to beat humans in a complex multiplayer competition". [1] The developers of the bot published their results in 2019. [2]

According to the Pluribus creators, "Developing a superhuman AI for multiplayer poker was the widely recognized main remaining milestone" in computer poker prior to Pluribus. Pluribus relies on offline self-play to build a base strategy, but then continues to learn in real-time during its online play. The base strategy was computed in eight days, and at market rates would cost about $144 to produce, much smaller than contemporary superhuman game-playing milestones such as AlphaZero. In AI, two-player zero-sum games (such as heads-up hold'em) are usually won by approximating a Nash equilibrium strategy; however, this approach does not work for games with three or more players. Pluribus instead uses an approach which lacks strong theoretical guarantees, but nevertheless appears to work well empirically at defeating human players. Across the competitions, Pluribus won an average of over 30 milli big blinds per game. Pluribus' self-learned play style avoids "limping" (calling the big blind), and engages in "donk betting" (ending a round with a call and starting the next round by betting) more often than human experts do. [2]

Among expert poker players, Jason Les stated he felt "very hopeless. You don't feel like there’s anything you can do to win." Chris Ferguson stated "Pluribus is a very hard opponent to play against. It's really hard to pin him down on any kind of hand." Jimmy Chou stated "Whenever playing the bot, I feel like I pick up something new to incorporate into my game." In The Wall Street Journal , science editor Daniela Hernandez characterized Pluribus as "advanced at a key human skill — deception". [3] [4]

Playing No-Limit Hold'em against five professional poker players, Pluribus won an average of $5 per hand with winnings of $1,000 per hour, which Facebook described as a "decisive margin of victory." [5] [6]

Following the victory, the developers declined to release the source code, out of fear it would be misused to surreptitiously cheat against human poker players in online matches. [7] [8]

Related Research Articles

<span class="mw-page-title-main">Poker</span> Card game

Poker is a family of comparing card games in which players wager over which hand is best according to that specific game's rules. It is played worldwide, but in some places the rules may vary. While the earliest known form of the game was played with just 20 cards, today it is usually played with a standard deck, although in countries where short packs are common, it may be played with 32, 40 or 48 cards. Thus poker games vary in deck configuration, the number of cards in play, the number dealt face up or face down, and the number shared by all players, but all have rules that involve one or more rounds of betting.

<span class="mw-page-title-main">Omaha hold 'em</span> Community card poker game

Omaha hold 'em is a community card poker game similar to Texas hold 'em, where each player is dealt four cards and must make their best hand using exactly two of them, plus exactly three of the five community cards. The exact origin of the game is unknown, but casino executive Robert Turner first brought Omaha into a casino setting when he introduced the game to Bill Boyd, who offered it as a game at the Las Vegas Golden Nugget Casino. Omaha uses a 52-card French deck. Omaha hold 'em 8-or-better is the "O" game featured in H.O.R.S.E.

<span class="mw-page-title-main">Texas hold 'em</span> Variation of the card game of poker

Texas hold 'em is one of the most popular variants of the card game of poker. Two cards, known as hole cards, are dealt face down to each player, and then five community cards are dealt face up in three stages. The stages consist of a series of three cards, later an additional single card, and a final card. Each player seeks the best five-card poker hand from any combination of the seven cards: the five community cards and their two hole cards. Players have betting options to check, call, raise, or fold. Rounds of betting take place before the flop is dealt and after each subsequent deal. The player who has the best hand and has not folded by the end of all betting rounds wins all of the money bet for the hand, known as the pot. In certain situations, a "split pot" or "tie" can occur when two players have hands of equivalent value. This is also called "chop the pot". Texas hold 'em is also the H game featured in HORSE and HOSE.

<span class="mw-page-title-main">Mike Caro</span> American poker player (born 1944)

Mike A. Caro is an American professional poker player, pioneer poker theorist, author of poker books, and casino executive.

<span class="mw-page-title-main">Jonathan Schaeffer</span> Canadian researcher and professor

Jonathan Herbert Schaeffer is a Canadian researcher and professor at the University of Alberta and the former Canada Research Chair in Artificial Intelligence.

<span class="mw-page-title-main">David Sklansky</span> American poker player and author

David Sklansky is an American professional poker player and author. An early writer on poker strategy, he is known for his mathematical approach to the game. His key work The Theory of Poker presents fundamental principles on which much later analysis is based.

A computer poker player is a computer program designed to play the game of poker, against human opponents or other computer opponents. It is commonly referred to as pokerbot or just simply bot. As of 2019, computers can beat any human player in poker.

<span class="mw-page-title-main">Tom McEvoy</span> American poker player and author (born 1944)

Thomas K. McEvoy is a professional poker player, author and member of the Poker Hall of Fame, 2013 inductee. He is best known for winning the 1983 World Series of Poker Main Event.

<span class="mw-page-title-main">Heads-up poker</span> Type of poker game

Heads-up poker is a form of poker that is played between only two players. It might be played during a larger cash game session, where the game is breaking up and only two players remain on the table, or where two players are trying to start a game and playing heads-up while waiting for other opponents. It is also a necessary phase in most sit-and-go (SNG) poker tournaments; the single remaining tournament winner will at some point have to face only a single opponent. Alternatively, heads-up poker may be played on purpose, either in a cash game format, or as a SNG, where two players play a winner-take-all tournament for a fixed, previously agreed upon amount of money. On larger online poker rooms and during certain tournament series, one may stumble upon larger heads-up tournaments, usually in the shoot-out format. Usually, in order to ensure the fairness of the game, all players finishing at the same level of the tournament bracket will be paid out the same amount of money, no matter what their finishing place is.

<span class="mw-page-title-main">Progress in artificial intelligence</span> How AI-related technologies evolve

Progress in artificial intelligence (AI) refers to the advances, milestones, and breakthroughs that have been achieved in the field of artificial intelligence over time. AI is a multidisciplinary branch of computer science that aims to create machines and systems capable of performing tasks that typically require human intelligence. Artificial intelligence applications have been used in a wide range of fields including medical diagnosis, economic-financial applications, robot control, law, scientific discovery, video games, and toys. However, many AI applications are not perceived as AI: "A lot of cutting edge AI has filtered into general applications, often without being called AI because once something becomes useful enough and common enough it's not labeled AI anymore." "Many thousands of AI applications are deeply embedded in the infrastructure of every industry." In the late 1990s and early 21st century, AI technology became widely used as elements of larger systems, but the field was rarely credited for these successes at the time.

<i>Bicycle Casino</i> (video game) 2004 video game

Bicycle Casino is a gambling game for the Xbox created by American developer Leaping Lizard Software and published by Activision Value on October 26, 2004. Described by the developer as a simulation of an "authentic casino environment", the game is a compilation of casino games licensed by Bicycle Playing Cards, with an advertised 500 variations on games including texas hold'em and blackjack. The game was marketed as the first casino title released for the Xbox to have featured multiplayer capabilities using Xbox Live. The game was released to generally mixed reviews, with publications praising the inclusion of online play, but critiquing the game's presentation and performance of AI players.

<i>Texas Holdem King</i> 2004 video game

The Texas Hold’em King franchise is a series of games for mobile devices based on the popular version of poker, Texas Hold 'em. Developed by Ottawa-based Magmic Games, the titles have been ported to a number of devices all leading to the latest version with varied features taking one version a step up from the last.

<span class="mw-page-title-main">Doug Polk</span> American poker player (born 1988)

Douglas K. Polk is an American professional poker player. Polk played under the alias WCGRider, specializing in heads-up No Limit hold'em (HUNL).

Cepheus is the first poker playing program that "essentially weakly solved" the game of heads-up limit Texas hold 'em. This was the first imperfect information game played competitively by humans to be essentially solved. It was developed by the Computer Poker Research Group (CPRG) at the University of Alberta and was introduced in January 2015 in a paper entitled "Heads-up limit hold’em poker is solved", published in Science by Michael Bowling, Neil Burch, Michael Johanson, and Oskari Tammelin.

Claudico is an artificial-intelligence computer-program designed to play no-limit Texas hold 'em heads-up.

Libratus is an artificial intelligence computer program designed to play poker, specifically heads up no-limit Texas hold 'em. Libratus' creators intend for it to be generalisable to other, non-poker-specific applications. It was developed at Carnegie Mellon University, Pittsburgh.

AlphaStar is a computer program by DeepMind that plays the video game StarCraft II. It was unveiled to the public by name in January 2019. In a significant milestone for artificial intelligence, AlphaStar attained Grandmaster status in August 2019.

DeepStack is an artificial intelligence computer program designed to play two-player poker, specifically heads up no-limit Texas hold 'em. It is the first computer program to outplay human professionals in this game.

Kate S. Larson is a Canadian computer scientist working as a professor, Pasupalak AI Fellow, and University Research Chair in the Cheriton School of Computer Science of the University of Waterloo.

Tuomas Sandholm is the Angel Jordan University Professor of Computer Science at Carnegie Mellon University and a serial entrepreneur with a research focus on the intersection of artificial intelligence, economics, and operations research.

References

  1. Solly, Meilan (15 July 2019). "This Poker-Playing A.I. Knows When to Hold 'Em and When to Fold 'Em". Smithsonian. Retrieved 23 February 2023.
  2. 1 2 Brown, Noam; Sandholm, Tuomas (11 July 2019). "Superhuman AI for multiplayer poker". Science. 365 (6456): 885–890. Bibcode:2019Sci...365..885B. doi: 10.1126/science.aay2400 . PMID   31296650.
  3. Vincent, James (11 July 2019). "Facebook and CMU's 'superhuman' poker AI beats human pros". The Verge. Retrieved 4 February 2021.
  4. Hernandez, Daniela (11 July 2019). "Computers Can Now Bluff Like a Poker Champ. Better, Actually". Wall Street Journal. Retrieved 4 February 2021.
  5. Brown, Noam; Sandholm, Tuomas (2019). "Superhuman AI for multiplayer poker". Science. 365 (6456): 885–890. Bibcode:2019Sci...365..885B. doi: 10.1126/science.aay2400 . PMID   31296650. S2CID   195892791.
  6. Brown, Noam (11 July 2019). "Facebook, Carnegie Mellon build first AI that beats pros in 6-player poker". ai.facebook.com. Retrieved 23 February 2023.
  7. Ouellette, Jennifer (11 July 2019). "Facebook AI Pluribus defeats top poker professionals in 6-player Texas Hold 'em". Ars Technica.
  8. Knight, Will (11 July 2019). "Facebook's new poker-playing AI could wreck the online poker industry—so it's not being released". MIT Technology Review.