How AI beat the best poker players in the world | Engadget R+D
Ғылым және технология
"That was anticlimactic," Jason Les said with a smirk, getting up from his seat. Unlike nearly everyone else in Pittsburgh's Rivers Casino, Les had just played his last few hands against an artificially intelligent opponent on a computer screen. After his fellow players -- Daniel McAulay next to him and Jimmy Chou and Dong Kim in an office upstairs -- eventually did the same, they started to commiserate. The consensus: That AI was one hell of a player.
Full story: www.engadget.com/2017/02/10/l...
Subscribe to Engadget on KZread: engt.co/subscribe
Get More Engadget:
• Like us on Facebook: / engadget
• Follow us on Twitter: / engadget
• Follow us on Instagram: / engadget
• Add us on Snapchat: / engadgethq
• Read more: www.engadget.com
Engadget is the definitive guide to this connected life.
Пікірлер: 711
can you imagine phil hellmuth playing against libratus? "it called with ace-ten honey!" "this computer is the worst poker player I've ever seen! really it probably won't last another hour!"
@arya6085
6 жыл бұрын
Mr Tomato what?
@pseudonym381
6 жыл бұрын
Arya Khonsari thats a Hellmuth quote
@winningbackthegirl
6 жыл бұрын
fuckin durrrrr
@superpasi7315
6 жыл бұрын
The AI probably can’t even spell Poker
@sggsdd1
6 жыл бұрын
Northern European hardware
I wonder how the study could go if for the first day you tell the players they are playing against an anonymous pro who is and in another room? I feel there can be a placebo effect with players being conscious of the AI. This was a very interesting report, thanks for posting!
@brianwillis8447
6 жыл бұрын
BigTeste my thoughts exactly. They went in trying to beat an bot, instead of trying to win the most money.
@andrewfraancis
6 жыл бұрын
A robot plays very differently to a human. You’d be able to tell it was a robot within an hour or so even if nobody told you.
Who would like to see Phil hellmuth play against this AI? That be funny as hell I imagine
@BlueEyesWhiteBoy
7 жыл бұрын
He called a raise with QT. Probably doesn't even know how to CODE poker.
@Illmatic69
7 жыл бұрын
Doppe1ganger "he 3 bet with Q 10 honey"
@Armmani2000
7 жыл бұрын
instantly laughed my ass off!
@cl4709
7 жыл бұрын
LMFAO "fucking moron AI, I had pocket tens!!"
@DJ_Shenanigan00
7 жыл бұрын
haa. he would die from rage
Talking about the latest technology in AI while sitting in front of a CRT monitor...
@devrim-oguz
7 жыл бұрын
+momentinpassing yeah, but CRT actually means Cathode Ray Tube, which is also cool. And by the way, they don't work with x-rays.
@andrewy3279
4 жыл бұрын
Maybe he's a smash melee fan
this proves poker is a game of skill
@bruceim3290
5 жыл бұрын
peppi1974 u mean poker is game of feel at got no feel
@bulbarobat
5 жыл бұрын
bullshit its prove only one thing - that time comp was lucky
@Scalpers.united
4 жыл бұрын
it proves that bots wil take over online poker by criminals
@TheMrKeksLp
4 жыл бұрын
Poker is still a game of luck. All the AI is doing is trying to approximate the Nash equilibrium strategy as closely as possible. It doesn't win by being "good" it wins by making less mistakes than humans
@burtgordon4796
4 жыл бұрын
Nullpointer but if it wins it is the better player. The better player makes fewer mistakes. It (the AI) doesn't get tired, frazzled, pissed, euphoric or impulsive.
Kassouf could make Libratus tilt by hand 4.
Hello Engadget, I would like to look at the played hands. Is it possible to see a record?
@insomnia20422
2 жыл бұрын
You realize that individually played hands are completely meaningless with this AI though right? It outplays you with the statistical data, the probability and value bet calculations overall. Thats why they needed to run so many hands to be sure it is better.
I forsee a future where a bearded Poker-playing AI with chicken leggs, is posting Instagram pictures filled with hired models, guns and luxurious mansions. And people will like the AI for that.
@user-dn2ud7jl6i
3 жыл бұрын
Hahahaha omg that so on point.
This is a monumentous task involving having to vary your strategy over time and even changing the rate at which you change strategies over time, whilst also having each style be concrete enough in order to not leave too much up to chance. All the while, the AI's model has a discrete memory. Since it's playing against multiple people and learning from them whilst still keeping individual strategies for individual players, they are playing against a machine with the solid foundations of many which can focus that knowledge in order to wreack havoc. Like a prized warrior faced by the collective efforts of a small army, terrifying and also very instructive and awe inspiring!
Does it learn from data specific to each player or that specific aggregate group and their various learn exploits? How would this scale if it was just a station game at a casino with no hand large hand history for whoever sat at the machine? Is it optimising for poker in general? or against the specific player and their data?
Anyone know what the ai looks like in a hud, like vpip 3 bet % etc
This was a great report. Always happy to see journalism at its finest in the age of fake news and improper journalism.
@AbirChoudhury101
7 жыл бұрын
Engadget is a web magazine. Magazines are under the umbrella of journalism.
@JacobHG1234
7 жыл бұрын
They are not the best HU players in the world tho.. Which kinda sucks, would be great to see the comp vs the best of the best. They're very good pros.. but best HU they are not.
@AbirChoudhury101
7 жыл бұрын
Mr J Bean I completely agree with you
@storiesfromthedash6980
7 жыл бұрын
Indeed. But pewdiepie still has 150 times more subs.
@RoiAleTea
7 жыл бұрын
tfw this is actually fake news too... The test is flawed, they are playing mirrored hands and are equity chopping all in scenarios which fundamentally changes the game and the way mirrored hands should work. Dong Kim explains this in his interview with Doug Polk
"just in libratus fashion" lmfao how many times did the robot suckout loooool
"Genomic research, improving society..." LIBRATUS..Libr-rat-us... Liberate Us?... Yea, this is some WestWorld shit.
@PseudoAccurate
7 жыл бұрын
Libratus means "balanced" in Latin.
@EricSmyth2Christ
7 жыл бұрын
Lab Rat Us.
@ketchup143
7 жыл бұрын
tbh i thought it had something to do with liberation as well
where do i download libratus?
can anyone tell me how do i play against AI myself i want to try it is there any program/download i can use?
I would like to see if there would be any variance if the cards were real and the info of the hand was inputted into the Libratus instead of playing the game in the computer that has Libratus on it.
@insomnia20422
2 жыл бұрын
you think they cheat on their own science project?
The Ai are or is reading the cards on the screen through your eyes is how it improves it moves each game.
AI strategy is both amazing and kind of terrifying.
@insomnia20422
2 жыл бұрын
also in poker it is basically about tricking players, so if AI starts beating us in this... oh boy...
Does this system use players hole card information to collect this data or just what it learns from show downs?
In this poker game, is there a cutoff point where you know the average of hands is better or worse than what you currently have?
Who deals the cards in beginning
I'm wondering if it took 20 days of poker play for Libratus to solve the game? Can it fair as well in a normal poker time frame like 3-8 hours of gameplay?
how can i download this?
I am really interested in seeing how Libertus adapt his play when facing itself. I can reason that it would reach several stationary states all of which are only metastable. The issue is how can it closely approach the optimal strategy while the other Liberatus is doing the same. Also it is amazing how easily Liberatus drifts far away from GTO to exploit the opponent! Great job!
@insomnia20422
2 жыл бұрын
thats probably how you could create, similar to neural network chess engines, an opponent independant ultra-strong AI of course it would be weaker than the adaptive one but it still but be superhuman
The most interesting bit is that, if the network was trained against a computer algorithm it would learn the loopholes embedded within its syntax. When trained against a human it is learning our flaws and mannerisms. I say we probably shouldn't strive for a general A.I unless we wish to be fully displaced.
@sameasnow
6 жыл бұрын
Luke Bitton tell prometheus that
@jun1orbaitor44
6 жыл бұрын
Luke Bitton EXACTLY. Do they not see the simple and almost certain future in creating this??
@insomnia20422
2 жыл бұрын
that train is long gone and noone will stop it
5:20: How did he arrive at that figure? Don't get me wrong, the number of possible situations that can occur in a full ring game are incalculable, but the amount of possible permutations in a HU game is roughly 5.75 quadrillion.
where is the download link?
Be interesting to see these sessions cards up
Anyone got a link for free download?
do u have API ? ))
I'm sure this greatly improved those HU players game.
Sweet video. Thank you.
can i download this somewhere XD
why didnt they have a hud
A win win for all of us great work.
Guys please try to remember that full ring NLHE is still very far from being solved.
@DoctorChained
3 жыл бұрын
AI beat vs 5 pros in a 6 max game
@insomnia20422
2 жыл бұрын
not sure about "very" far and solved for me means superhuman, because solved is obviously impossible in an incomplete information game
I like how he keeps calling them humans
@EricSmyth2Christ
7 жыл бұрын
hahaha
One of the biggest advantages to AI. There is no fear of losses or mistakes.
Yep, AI can make very weird moves that you rarely see high level players use, it's just because they can go through every scenario that pro level players don't consider due to an undiscovered way of thinking. Chess, poker, whatever. Any player that played with an AI can notice a difference.
@mcpartridgeboy
7 жыл бұрын
well said, some of the chess moves those machines play are obvious machine moves, !
@amadexi
3 жыл бұрын
It's tue that old style AI's (hard-coded logic with future-move analysis) often have really weird moves. But modern Neural-network AI's do learn like humans (from other humans, through experience, just at a really high rate) and have much more human-like moves. In fact, AlphaZero, the version of the Alpha AI that leans without being fed human game replays, has rediscovered many human strategies by itself. AI's in much more complex real-time games (like DOTA and StarCraft) do also play a bit like humans (although they feel oddly smart and skilled), and show human-like behaviour like faking, baiting, smart exploiting of game mechanics,... But when they feel inhuman, it is mostly because they have much more experience, they have seen and played millions of games.
1. Those players are not "absolute best". Far from it 2. The player hadn't had the usual incentive to play to win. 3. The players chose to play as a marathon (being tired), to get the same money in less days 4. It's a statistical tie (insider joke)
@raabsand
6 жыл бұрын
I was thinking some of these exact things
@isaacvongurtberg7341
5 жыл бұрын
Denial
@jorginhojoji4520
5 жыл бұрын
@@isaacvongurtberg7341 Valid tagging while not even trying to refute, PUSSY
@jburch5752
4 жыл бұрын
They are very good players but not the "best" in the world. Also, the computer can not predict what cards are coming out next. Nor would it know what you mucked. Also, the computer has a bit of an advantage because it can instantly calculate odds that would be too complicated for a human, especially since humans get tired. I would like to see it play against a mix of regular players and much higher level players. Also, the computer is playing unfairly. Human plays aren't bringing their charts, computers, calculators, or consulting outside sources. Level the playing field and let the humans use any resources they want which would cut down of fatigues and human error.
@powerlifting1012
4 жыл бұрын
@@jburch5752 I think they were using some tools to analyze what was working and not working but yes you are right computers can do calculations in second. I'm reading the poker blueprint and the formula to find ev is too long to do each hand. That's why we have to just estimate and review later unlike computers
Go Donger Kim with the smallest loss!
Lol Phil helmuth stands up at the computer, rips out his headphones. Yells at the computer "you are a idiot friend" lol
Questions:- 1) Did the blinds increase over time or were blinds the same through out the competition? Could the computer account for the Blinds increasing? 2) Could the AI in its present form compete at a 10 person table tournament? 3) What other games left does google AI want to compete in?
@scrowtymcbuggerballs5539
7 жыл бұрын
misomiso It won't be a tournament format It'll be a cash format with less variance. They may play at different stack sizes though
@chessbrainiac
7 жыл бұрын
1. The blinds stayed the same throughout. Also each hand started with both players having a 20k stack. So each hand both players were equally deep. 2. This is just a guess, but I wouldn't be surprised if it would do reasonably well. The team behind Libratus has said that in their estimates Libratus could crush 6-max in 2 years. I think this is a careful estimate, and believe it can be done sooner if they put their effort on doing it. 3. Your guess is as good as mine here.
Have a computer on the side playing online poker and each hand you play just enter the exact cards you have and the flops then let the Ai tell you what to do. Mark witch position is checking or raising and let the computer give you the next move. (Example, fold because that that that or 3 bet because i see weakness, you will win millions) I’m programming my own poker AI assistant for online games
Poker sites could offer this as an opponent as a sort of "Beat the AI" challenge.
Libratus should "check its privilege"
@DaveGeelen88
7 жыл бұрын
hahaha
@ericblair7357
6 жыл бұрын
untouchable360x lololol
So the professor himself coded and thought out the whole project himself? That would be a first.
This sh*t is going to destroy online poker
@mehdinadif
7 жыл бұрын
Ruben Ernst once a supercomputer becomes available to the general population, sure
@Manuel013
7 жыл бұрын
mehdinadif you don't need a supercomputer to run AI software
@mehdinadif
7 жыл бұрын
Manuel LK check the video, liberatus specifically needs a supercomputer to perform its calculations.
@TheMASDrummer
6 жыл бұрын
It doesn't work in anything apart from heads up NL. There is no nash equaliblium in 6max.
@ericblair7357
6 жыл бұрын
Ruben Ernst going to destroy humanity
That AI is like pokerstars micro players.
What if you make the AI vs the AI ?
@Kosaro1234
7 жыл бұрын
It played against itself trillions of times, constantly adjusting its algorithms. That's how it got so good.
@ericblair7357
6 жыл бұрын
Daniel F boom mind blown
@andrewfraancis
6 жыл бұрын
Would be fun to watch to be fair
@MsJavaWolf
6 жыл бұрын
Libratus is likely the best bot at this point, but you can check out the Anual Computer Poker Competition, where many good bots play against each other. Even an earlier bot from the makers of Libratus and other universities as well.
@Glocky131
4 жыл бұрын
Computer explode
Playing the AI is probably like playing against Shang Tsung in Mortal Kombat morphing into whatever style suits it better at the time.
I'm wondering how this AI would do in 6 handed sit&go's for example. I'll bet that it won't be long before most poker sites will use a version of this AI to consolidate and probably even increase their margins. And I'm wondering how long it will before an AI will win the WSOP using 'speech play'?!! Like a boss!!
@Donstroyer
7 жыл бұрын
"How many miles from here to silicon valley?"
@fritzov
7 жыл бұрын
InfiniteCyclus 6max sngs can easily be besten by bots Today. Its basically just math, Cashgame HU is a complete differentierad story
@ParkerPlaysPC
7 жыл бұрын
6max sitngoes can be beaten by bots pretty easily. However, a bot beating a 6max cash game table over 100k hands would be extremely hard for a bot if all other 5 players were extremly talented (such as the ones in this video). It would be even harder to beat if it was a 9max cash table.
@yael2417
7 жыл бұрын
its not programmed for that,.,. im assuming its way more deepstacked so more skill intensive for 6handed lowskill game it would be different bot
@andrewfraancis
6 жыл бұрын
The theoretical problem with a 6 handed cash table is there are exponentially more situations that the bot could come across. Logically it would mean that they need a lot more computing power to pull it off than they do even now!
Really interesting. It would be interesting to see if Doug Polk, Isaac Haxton, Jonas Mols and Alex Millar could beat it
I, for one, welcome our new heads up no limit Texas hold 'em overlord.
I wish that it was available to the public like Poker Snowie!!
The guy with the moustache just sounds like a robot! Weird cadence.
About 14 seconds into the video made my siri go off? Anyone else experience this? My "hey siri" is turned on and my iphone is plugged in.
I need this for online poker
This was good. Can it win with a very finite amount of money to start with? I think that would be the real winner!
i wonder if they can develope an ai that can analyze your game and coach you
so if i use ai to play online poker match, then i can win alot of money while im sleeping?
Behind Libratus there is a real person. You can his picture on the top-left of the screen at 10:44
I think if players could see libratus' hands everytime it would be easier for them to adapt
@insomnia20422
2 жыл бұрын
libratus doesnt see players hands either, otherwise that would be way to easy
Ib4 the AI knew the opponents hand all along
Very interesting.
You should challenge Libratus against himself, would be interesting
@BlueEyesWhiteBoy
7 жыл бұрын
It played itself 100 trillion times. That's how it was created, the losing strategy trees were cut quickly.
@BlueEyesWhiteBoy
7 жыл бұрын
5:33 it explains it.
@ussnimitz3666
7 жыл бұрын
Reinforced learning brah
this is the ultimate weapon.
It's a crime that Noam Brown was not mentioned anywhere in the video or the description.
I'd like to see this play otb redbaron or Phil H
Put Ivey in there. I'm serious
@lozkokaramitev8027
6 жыл бұрын
I discovered a good compilation of videos that should help on card crusher fixer
@rogerdeleon7663
5 жыл бұрын
I agree; Ivey is not of this world!
@egenuch9844
5 жыл бұрын
Wait do any of you think there is a fighting chance if ivey play the AI?
@futurez12
5 жыл бұрын
The top online players would shit all over Ivey.
@BumsNJunkies
5 жыл бұрын
@@futurez12 No they wouldn't
I want to buy them out in any form of games
As a poker player, I wish I could play this AI! 😁
@Giletech
6 жыл бұрын
Try a 6-max THNL AI player
I wonder why they didn't apply a shove/fold strategy once they got down a bunch.
@Swarm_
7 жыл бұрын
goombas3040 i think they always started with 200 bb or something like that
@Swarm_
7 жыл бұрын
goombas3040 so they never had the chance to use that
Congrats to humans on statistical tie
@heartandtroll9993
7 жыл бұрын
Dude. Not a tie. The humans got crushed.
@hasepase
7 жыл бұрын
last year their bot got crushed in almost the same way it did the humans this year but the company declared it a statistical tie in an official report. so gratz on a statistical tie.
@heartandtroll9993
7 жыл бұрын
Definitely not a statistical tie. Humans lost big time to the bot.
@hasepase
7 жыл бұрын
well, did you see the results of the last years challenge? when that was a statistical tie this is also one.
@heartandtroll9993
7 жыл бұрын
Sorry, dude. Not how it works. Getting crushed is getting crushed.
I'm sure this AI is somehow sexist, but I haven't figured out how exactly..
@MrCaptainTea
3 жыл бұрын
The AI is actually a feminist
And this is how hydra started
It would be intereesting to see a total rookie being told what to do by the program playing against a pro. I wonder if the pros could read the rookies.
The players you brought programed it
So it plays like Stu Ungar used to, nice.
No fatigue, opponents with no information about itself.
and so it begins...
I want to see an AI developed to beat the best TCG players.
@i_i8924
2 жыл бұрын
AI flips over set Heavy Storm
I would to be part of this!
Anyone else think the two scientists speak like robot text people use on KZread videos?
awesome
ok, so the next challenge is tournament poker.
Congratulations KZread ai for finding me something interesting for a change!
Okay, now play 100,000 big blinds deep. =)
@mrvetle
5 жыл бұрын
Makes it even harder for humans
As for the best strategy for improving odds, considering the ai has better statistical data, strategy, and is overall steps ahead of the player, I think the best odds you have are going all in on premium/high valued probability hands, as the players started to do. The ai will still beat you at valueing it's hand, but by making it all in every time, it removes the river, flop, and turn betting strategies, and puts more into preflop odds, as well as limit the ammount of hands the game is played, limiting how much the statistics effects the outcome. Although, the ai would win over 50%, I presume this is the closest you could get it to even win/loss. Simply do your best to remove all strategy from the game, and put your chips in on luck.
@insomnia20422
2 жыл бұрын
exactly, the more complicated you make the game (and the background data, probability, value handling), the more you will get outplayed by the AI
i somehow believe overbetting turn card makes river plays much easier ! Ofc you need to be in possition/ALWAYS! If you're out of possition you should ALWAYS play trap game no matter if u AA or 72 holding.
I understand that they're probably more interested in the practical applications of this AI, but I would LOVE to have Libratus play itself for thousands of hours until it converges (or comes close) to the Nash Equilbirum for HUNL. It would really improve the level of human players, in much the same way that chess engines have vastly improved the play of chess professionals.
@TomAKAsP3ctRum
7 жыл бұрын
solving HUNL or coming close to solving it is def not possible with the current state of computer power
@ianhoward1518
7 жыл бұрын
So what would happen if you pitted this algorithm against itself? Would it basically never converge and just have the strategies oscillating around equilibrium?
@TomAKAsP3ctRum
7 жыл бұрын
i am just saying that the raw computing power that is necessary to solve HUNL is just not there yet. As the video says, there are like 10^160 scenarios and therefore a huge number of game trees each with different possible bet sizings etc.
@maximkazhenkov11
7 жыл бұрын
Finding the Nash equilibrium for Texas Holdem is like finding the perfect strategy (God's hand) for chess or Go; it's impossible with a computer smaller than the observable universe. But I imagine it should be possible to go far beyond the best human player, albeit the result is less apparent since victory is still dependent on chance.
@ebelsa
7 жыл бұрын
I'm pretty sure Libratus playing trillions of hands against itself is how it devised its initial strategy vs. the humans.
Our future will depend on the best military Ai coder lol
The comment at the end that AI is always helping mankind is what so many scientists/futurists are worried about. Programming AI with that kind of amorphous, subjective criteria is beyond difficult. Awesome story here, regardless.
Would be interesting to se linus vs this bot over a sample.
Nothing here mentions quality of life hahahaha!
Not even watching the entire video because the title already sums it up. It should be "Can AI beat the best poker players in the world?", then i'd be watching the entire vid.
@alanfrost75
7 жыл бұрын
While I do kind of agree with you, the interesting part of the video was why (and how).
why does the one professor literally sound like microsoft sam
0:25 This guy sounds like an AI.
where is Doug Polk gone?