Libratus

Last updated

Libratus is an artificial intelligence computer program designed to play poker, specifically heads up no-limit Texas hold 'em. [1] Libratus' creators intend for it to be generalisable to other, non-poker-specific applications. It was developed at Carnegie Mellon University, Pittsburgh.

Contents

Background

While Libratus was written from scratch, it is the nominal successor of Claudico. Like its predecessor, its name is a Latin expression and means 'balanced'.

Libratus was built with more than 15 million core hours of computation as compared to 2-3 million for Claudico. The computations were carried out on the new 'Bridges' supercomputer at the Pittsburgh Supercomputing Center. According to one of Libratus' creators, Professor Tuomas Sandholm, Libratus does not have a fixed built-in strategy, but an algorithm that computes the strategy. The technique involved is a new variant of counterfactual regret minimization, [2] namely the CFR+ method introduced in 2014 by Oskari Tammelin. [3] On top of CFR+, Libratus used a new technique that Sandholm and his PhD student, Noam Brown, developed for the problem of endgame solving. Their new method gets rid of the prior de facto standard in Poker programming, called "action mapping".

As Libratus plays only against one other human or computer player, the special 'heads up' rules for two-player Texas hold 'em are enforced.

2017 humans versus AI match

From January 11 to 31, 2017, Libratus was in a tournament ("Brains vs. Artificial Intelligence: Upping the Ante challenge") against four top-class human poker players, [4] namely Jason Les, Dong Kim, Daniel McAulay and Jimmy Chou. In order to gain results of more statistical significance, 120,000 hands were to be played, a 50% increase compared to the previous tournament that Claudico played in 2015. To manage the extra volume, the duration of the tournament was increased from 13 to 20 days.

The four players were grouped into two subteams of two players each. One of the subteams was playing in the open, while the other subteam was located in a separate room nicknamed 'The Dungeon' where no mobile phones or other external communications were allowed. The Dungeon subteam got the same sequence of cards as was being dealt in the open, except that the sides were switched: The Dungeon humans got the cards that the AI got in the open and vice versa. This setup was intended to nullify the effect of card luck.

The prize money of $200,000 was shared exclusively between the human players. Each player received a minimum of $20,000, with the rest distributed in relation to their success playing against the AI. As written in the tournament rules in advance, the AI itself did not receive prize money even though it won the tournament against the human team.

During the tournament, Libratus was competing against the players during the days. Overnight it was perfecting its strategy on its own by analysing the prior gameplay and results of the day, particularly its losses. Therefore, it was able to continuously straighten out the imperfections that the human team had discovered in their extensive analysis, resulting in a permanent arms race between the humans and Libratus. It used another 4 million core hours on the Bridges supercomputer for the competition's purposes.

During the tournament, there was an active betting market among poker players about who would win the tournament. It started with 4:1 against the bot, but on the 8th day it became a betting market on which human would lose the least. [5] : 07:30 .

Strength of the AI

Libratus had been leading against the human players from day one of the tournament. The player Dong Kim was quoted on the AI's strength as follows: "I didn’t realize how good it was until today. I felt like I was playing against someone who was cheating, like it could see my cards. I’m not accusing it of cheating. It was just that good." [6]

At the 16th day of the competition, Libratus broke through the $1,000,000 barrier for the first time. At the end of that day, it was ahead $1,194,402 in chips against the human team. At the end of the competition, Libratus was ahead $1,766,250 in chips and thus won resoundingly. As the big blind in the matches was set to $100, Libratus' winrate is equivalent to 14.7 big blinds per 100 hands. This is considered an exceptionally high winrate in poker and is highly statistically significant. [7]

Of the human players, Dong Kim came first, MacAulay second, Jimmy Chou third, and Jason Les fourth.

NameRankResults (in chips)
Dong Kim1-$85,649
Daniel MacAulay2-$277,657
Jimmy Chou3-$522,857
Jason Les4-$880,087
Total:-$1,766,250

The bot has an unconventional betting style where under specific situations it would bet $20,000 even when there's $100 in the pot. After its win, this strategy was analyzed and adopted by the poker community. [5] : 55:25 

Other possible applications

While Libratus' first application was to play poker, its designers have a much broader mission in mind for the AI. [8] The investigators designed the AI to be able to learn any game or situation in which incomplete information is available and "opponents" may be hiding information or even engaging in deception. Because of this Sandholm and his colleagues are proposing to apply the system to other, real-world problems as well, including cybersecurity, business negotiations, or medical planning. [9]

See also

Related Research Articles

<span class="mw-page-title-main">Bluff (poker)</span> Tactic in poker and other card games

In the card game of poker, a bluff is a bet or raise made with a hand which is not thought to be the best hand. To bluff is to make such a bet. The objective of a bluff is to induce a fold by at least one opponent who holds a better hand. The size and frequency of a bluff determines its profitability to the bluffer. By extension, the phrase "calling somebody's bluff" is often used outside the context of poker to describe situations where one person demands that another proves a claim, or proves that they are not being deceptive.

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.

In video games, artificial intelligence (AI) is used to generate responsive, adaptive or intelligent behaviors primarily in non-playable characters (NPCs) similar to human-like intelligence. Artificial intelligence has been an integral part of video games since their inception in the 1948, first seen in the game Nim. AI in video games is a distinct subfield and differs from academic AI. It serves to improve the game-player experience rather than machine learning or decision making. During the golden age of arcade video games the idea of AI opponents was largely popularized in the form of graduated difficulty levels, distinct movement patterns, and in-game events dependent on the player's input. Modern games often implement existing techniques such as pathfinding and decision trees to guide the actions of NPCs. AI is often used in mechanisms which are not immediately visible to the user, such as data mining and procedural-content generation. One of the most infamous examples of this NPC technology and gradual difficulty levels can be found in the game Punch-Out!!.

In video games, a bot or drone is a type of artificial intelligence (AI)–based expert system software that plays a video game in the place of a human. Bots are used in a variety of video game genres for a variety of tasks: a bot written for a first-person shooter (FPS) works differently from one written for a massively multiplayer online role-playing game (MMORPG). The former may include analysis of the map and even basic strategy; the latter may be used to automate a repetitive and tedious task like farming.

Game Description Language (GDL) is a specialized logic programming language designed by Michael Genesereth. The goal of GDL is to allow the development of AI agents capable of general game playing. It is part of the General Game Playing Project at Stanford University.

Polaris is a Texas hold 'em poker playing program developed by the computer poker research group at the University of Alberta, a project that has been under way for 16 years as of 2007. Polaris is a composite program consisting of a number of bots, including Hyperborean08, the winner of the limit equilibrium series in the 2008 Association for the Advancement of Artificial Intelligence (AAAI) Computer Poker Competition. Polaris also contains a number of other fixed strategies, and chooses between these strategies during a match. Polaris requires little computational power at match time, so it is run on an Apple MacBook Pro laptop during competitions. Polaris plays only heads-up Limit Texas hold'em.

There are a number of competitions and prizes to promote research in artificial intelligence.

<span class="mw-page-title-main">Michael L. Littman</span> American computer scientist

Michael Lederman Littman is a computer scientist, researcher, educator, and author. His research interests focus on reinforcement learning. He is currently a University Professor of Computer Science at Brown University, where he has taught since 2012.

Duplicate poker is a variant of the card game poker. Duplicate poker is based on the principles of duplicate bridge, but it also incorporates some of the rules of pot limit and no limit Texas hold'em.

<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.

<span class="mw-page-title-main">Computer game bot Turing test</span>

The computer game bot Turing test is a variant of the Turing test, where a human judge viewing and interacting with a virtual world must distinguish between other humans and video game bots, both interacting with the same virtual world. This variant was first proposed in 2008 by Associate Professor Philip Hingston of Edith Cowan University, and implemented through a tournament called the 2K BotPrize.

<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.

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.

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". The developers of the bot published their results in 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.

The AAAI Award for Artificial Intelligence for the Benefit of Humanity is an annual prize given by the Association for the Advancement of Artificial Intelligence to recognize the positive impacts of AI to meaningfully improve, protect, and enhance human life. The award is presented annually at the AAAI conference in February. In its first two years, the associated reward was US$1 million, but has since been changed to $25000. Funding is provided by the Chinese online education company Squirrel AI.

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. ↑ Brown, Noam; Sandholm, Tuomas (2018-01-26). "Superhuman AI for heads-up no-limit poker: Libratus beats top professionals". Science. 359 (6374): 418–424. doi:10.1126/science.aao1733. ISSN   0036-8075.
  2. ↑ Hsu, Jeremy (10 January 2017). "Meet the New AI Challenging Human Poker Pros". IEEE Spectrum. Retrieved 2022-01-10.
  3. ↑ Brown, Noam; Sandholm, Tuomas (2017). "Safe and Nested Endgame Solving for Imperfect-Information Games" (PDF). Proceedings of the AAAI Workshop on Computer Poker and Imperfect Information Games.
  4. ↑ Spice, Byron; Allen, Garrett (January 4, 2017). "Upping the Ante: Top Poker Pros Face Off vs. Artificial Intelligence". Carnegie Mellon University. Retrieved 2017-01-12.
  5. 1 2 Noam, Brown (2024-09-17). Parables on the Power of Planning in AI: From Poker to Diplomacy: Noam Brown (OpenAI) (Video). Retrieved 2024-09-24– via YouTube. Lecture at Paul G. Allen School on Thursday, May 23, 2024, 3:30 pm
  6. ↑ Metz, Cade (24 January 2017). "Artificial Intelligence Is About to Conquer Poker—But Not Without Human Help". Wired. Retrieved 2017-01-24.
  7. ↑ "Libratus Poker AI Beats Humans for $1.76m; Is End Near?". PokerListings. 30 January 2017. Retrieved 2018-03-16.
  8. ↑ Knight, Will (January 23, 2017). "Why it's a big deal that AI knows how to bluff in poker". MIT Technology Review.
  9. ↑ "Artificial Intelligence Wins $800,000 Against 4 Poker Masters". Interesting Engineering. 27 January 2017.
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.