Program Poker Ai
(Bloomberg)— Facebook Inc. doesn’t just own the world’s largest social network — it may also own the world’s best poker player.
Artificial intelligence reached a milestone recently. Scientists at Carnegie Mellon developed a program called Pluribus that can beat humans at six-player Texas hold ’em poker. (Not all poker bots and AI research in the field is public because of the temptation to use one's results in internet poker, though that's forbidden.) First you should decide what sort of poker are you going to tackle first. Two player hold'em is pretty much solved, though the best humans still put up a real fight with the best AI's available. Poker Tracker 4 is a great program, but in my opinion, Holdem manager 3 is by far better. The main reason for that is vsHero stats – an option allowing you to see how your opponent’s plays specifically versus you and this could easily be a game changer when you play versus the same opponents a lot of the time. A poker bot, designed by researchers from Facebook’s AI lab and Carnegie Mellon University, has bested some of the world’s top players in a series of games of six-person no-limit Texas Hold ‘em. Researchers at Carnegie Mellon University, working with Facebook's AI initiative, announced on Thursday that their program defeated a group of top pros in six-player no-limit Texas hold'em poker. All those human players are best players in the world who have won more than $1 million playing poker, according to the study.
A new artificial intelligence program the company built with Carnegie Mellon University called Pluribus recently beat five poker professionals in a six-player Texas Hold’em tournament. After 10,000 hands, the system averaged profits of about $1,000 per hour using $1 chips, a “decisive margin of victory,” according to a Facebook blog post.
AI has been besting humans at poker for a couple of years, but previous programs could compete with just a single player at a time. Given the complexities that come with poker, including techniques like bluffing, beating five humans in a single game is a significant milestone, Facebook said.
“No other game embodies the challenge of hidden information quite like poker, where each player has information (his or her cards) that the others lack,” Facebook wrote in a blog post. “A successful poker AI must reason about this hidden information and carefully balance its strategy to remain unpredictable while still picking good actions.”
Building a poker superstar may seem like an odd use of AI resources given Facebook has so many other issues. The social network is still facing a constant battle against fake news and other types of misleading, troubling and dangerous content. When video of a live shooting was uploaded to Facebook in March, duplicates were uploaded 1.5 million times and more than 20% of them slipped past Facebook’s AI systems.
Facebook AI Research, the group behind the poker bot, isn’t developing AI for any specific product, said Noam Brown, the company researcher who led the card-playing work. Instead, the group is looking at AI more broadly, with the hope of applying its findings to industrywide problems. Many of the hardest challenges facing AI programs, like navigating a self-driving car through traffic or understanding human negotiations, include “hidden information,” similar to poker.
“The techniques are general enough to go beyond poker,” Brown said. “That’s the goal.”
The Leadership Brief. Conversations with the most influential leaders in business and tech.
Thank you!
For your security, we've sent a confirmation email to the address you entered. Click the link to confirm your subscription and begin receiving our newsletters. If you don't get the confirmation within 10 minutes, please check your spam folder.Libratus is an artificial intelligence computer program designed to play poker, specifically heads up no-limitTexas hold 'em. Libratus' creators intend for it to be generalisable to other, non-Poker-specific applications. It was developed at Carnegie Mellon University, Pittsburgh.
Background[edit]
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,[1] namely the CFR+ method introduced in 2014 by Oskari Tammelin.[2] 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[edit]
From January 11 to 31, 2017, Libratus was pitted in a tournament against four top-class human poker players,[3] 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.
Strength of the AI[edit]
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.'[4]
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.[5]
Of the human players, Dong Kim came first, MacAulay second, Jimmy Chou third, and Jason Les fourth.
| Name | Rank | Results (in chips) |
|---|---|---|
| Dong Kim | 1 | -$85,649 |
| Daniel MacAulay | 2 | -$277,657 |
| Jimmy Chou | 3 | -$522,857 |
| Jason Les | 4 | -$880,087 |
| Total: | -$1,766,250 |
Other possible applications[edit]
While Libratus' first application was to play poker, its designers have a much broader mission in mind for the AI.[6] 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.[7]
See also[edit]
References[edit]
- ^Hsu, Jeremy (10 January 2017). 'Meet the New AI Challenging Human Poker Pros'. IEEE Spectrum. Retrieved 2017-01-15.
- ^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.
- ^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.
- ^Metz, Cade (24 January 2017). 'Artificial Intelligence Is About to Conquer Poker—But Not Without Human Help'. Wired. Retrieved 2017-01-24.
- ^'Libratus Poker AI Beats Humans for $1.76m; Is End Near?'. PokerListings. 30 January 2017. Retrieved 2018-03-16.
- ^Knight, Will (January 23, 2017). 'Why it's a big deal that AI knows how to bluff in poker'. MIT Technology Review.
- ^'Artificial Intelligence Wins $800,000 Against 4 Poker Masters'. Interesting Engineering. 27 January 2017.
External links[edit]
- Brains versus Artificial Intelligence official website at the Rivers Casino