Humans Can Still Out-Bluff Machines

Pcol writes "The New York Times reports that in a poker game this week between man and machine, a program called Polaris fought a close match, but lost to two well-known professional poker players. Designing a poker playing algorithm is a different and more difficult challenge for software designers than chess and checkers because of uncertainties introduced by the hidden cards held by each player and difficult-to-quantify risk-taking behaviors such as bluffing. The game-tree approach doesn't work in poker because in many situations there is no one best move and a top-notch player adapts his play over time, exploiting his opponent's behavior. Polaris build a series of "bots" that have differing personalities or styles of play, ranging from aggressive to passive. Researchers monitored the performance of three bots and then moved them in and out of the lineup like football players."

Not harder than chess

[jshriverWVU (810740)]

In poker you have a finite number of cards, that are a lot smaller than the permutation of moves in chess or checkers. Just the ability to count cards and do statistical analysis makes poker, blackjack, etc easier to compute in my opinion. Then again, if you had a deck of random cards and not a standard deck, that would make it a bit harder but that's not how it's really played. That would be like comparing it to chess with all queens.

Re:Not harder than chess

[TheMeuge (645043)]

If you're playing cards in Hold'em, against decent players, you WILL lose.

Hold'em is all about betting - if, when, and how much. And THAT you determine by the behavior of your opponent. It's not a strategy game, but a psychological exercise.

Re:Not harder than chess

[xero314 (722674)]

[poker is] not a strategy game, but a psychological exercise.

Poker is indeed a strategy game. Knowing statistics and probability are critical to successful poker play. Psychology is important was well but is useless with out strategic knowledge. The majority of poker played in the world is limit poker which has far less psychological play and a lot more statistical accuracy. Even in a No Limit Hold'em game, probably the most psychological game regularly played, you would be better off having strong strategic and analytical skills an poor psychological skills than the other way around. But, like any game which contains aspect of chance, both strategy and psychology are imperative to being a successful player.

If you're playing cards in Hold'em, against decent players, you WILL lose.

I would be happy to take on any player, no mater what there record is, as long as that player never looks at his hole cards. Cards are important in card games, even if betting is the determining factor in who ultimately takes a particular pot. Imagine the game being played with no cards what so ever and you will see why knowing how to work with the cards you have is important to the game. Any time a professional player makes a "call" it is because of statistical knowledge and not psychological, even if it is to set up a play later on.

Re:Not harder than chess

[c_jonescc (528041)]

Being that the CS folks that setup the computer were expecting a draw, I think they must have started with the assumption that a top level pro poker player knows the statistics of almost every situation (from experience and intuition) as well as a machine can calculate them. And the truth is they do - the best probably know what their hole cards and flop mean down to the first decimal point every single time it's worth thinking about.

So, then the play comes down to responding to how the other person is playing. And the edge goes to the one that can safely be unreadable/unpredictable/inconsistent.

Now, obviously if you can't figure out any of the statistics involved in a hand you will always get your ass handed to you in the long run by a player/machine that can do the most rudimentary calculation.

Re:

[xero314 (722674)]

I'd venture to say that pot-limit omaha high is a *far* more psychological game

I agreed 100% and would put most stud games even above omaha in the amount of psychology in the game, but I said "played regularly" which from my experience limits the games to Texas Hold'em, Omaha hi/lo and 7 Stud hi/lo, and usually only limit for the later two, since they are the most common spread games, at least in the united states. I have actually never seen a Pot Limit Omaha High game in any casino I have been in and that's not a small number (though I am holding an HA rotation next week so I am cer

Re:Not harder than chess

[SIIHP (1128921)]

"I'd venture to say that pot-limit omaha high is a *far* more psychological game."

You'd be wrong. I made my living for two years playing PLO almost exclusively, at a high level (fuck you UIGEA and everyone who voted for you). The general consensus among students of the game is that PLO is one of the least psychological games played. The lack of bluffing being the major reason. Bluffing occurs, but the very same reason you cite as making it more psychological is why you're wrong the number of hands played. Playing such a large number of hand (50% is insane, and I challenge you to show me some poker tracker stats of someone who wins playing 50% of their hands long term). In fact, if a computer were to win consistently, I think PLO is a game that it would play.

"I don't think there's a difference between statistical knowledge and psychology."

Then let me learn you up. Let's use PLO. I have A-A-10-J double suited. I raise pot preflop. A VERY tight player reraises, and I call. Flop come K-K-K. Against an aggro player, I can reasonably infer that my 2nd nuts is good. Against Mr. Tighty, who I have seen reraise only with large suited pairs (KKJQ, QQJ10) or rundown hands (9-10-J-Q, 10-J-Q-K) I know within a certain range what he's holding, with some certainty. I am first to act, I check, he bets, I raise, and Mr. Tighty RERAISES. Based on my assessment of his likely behavior (psychology) I can reasonably infer that he has the K. Statistically, you NEVER lay down K's full of A's, but when your read (psychology) is good and the opponent is uncreative and direct (psychology) you lay it down.

Statistically the correct play is to put it all in if you can, but by understanding the other players decision making process (psychology) you can find a fold.

You're wrong again

Re:

[xero314 (722674)]

Statistically, you NEVER lay down K's full of A's...

If you actually think this is true you are using some bad statistics. I don't think that you do think it is true as you said yourself you would fold in the described situation. Even if you are taking all other information out of the equation statisiticaly K's full of A's (with 3 Ks on board) will lose approximately 1 in 11 times (opponent has 4 chances to have a king out of the 45 unseen cards). This means statistically you should lay down kings full of aces 1 out of every 11 times you play, but you woul

Re:

[Bender0x7D1 (536254)]

I think the point is that you don't know if it is the 1 time you lose, or the 10 times you win, so you would go for the win since, 10 out of 11 times, you would win. Who cares if you lose that 1 time if you win the other 10 times. That's why you never lay them down since, statistically, you are 10 times more likely to win than lose.

Re:

[joss (1346)]

Sancitmonious tripe. Those who lose money from poker do so voluntarily
so its a a form of entertainment they pay for. Professional poker
players are no more a leach on society than opera singers.

Old joke ,,,

[Tungbo (183321)]

Father explains the statistics of roulette to his son.
He shows how in the long run, all players will lose to the casino.
His son nods and nods with his explanation. At the end,
the father said, "Well son, have you learn anything from this lession?"

"Yes indeed. I'm going to open a casino when I grow up!"

Re:Not harder than chess

[xero314 (722674)]

There are plenty of times a pro player makes a call believing they have the worst hand, in order to bluff the hand later.

You are correct, but again this is because of statistical knowledge. A good player has determined in their own head what they believe the statistical chances are of their opponent having both a hand they can't call with and their opponent will believe that they themselves have a winning hand. Not only that the player making the call also has to determine if they odds are correct to try and set up a bluff like that in case their opponent has a draw and how good that draw is. If you are making any move in poker without first making a educated guess as to the odds, and determining that those Odds are in your favor, then you are leaving your odds up to chance and this is not how to be a successful player.

Re:

[Dan D. (10998)]

It's not a strategy game, but a psychological exercise.

One could imagine that a "psychological exercise" is still a strategy game, but with much wider priors in the statistics.

Re:Not harder than chess

[Aaron England (681534)]

Thinking that poker is only about statistics and luck is the hallmarks of an inexperienced player. The simple truth is, if you make your bets on the odds that you will win the pot against a professional poker player you will lose with 99.999% certainty. Because a professional poker player doesn't just play the odds, he plays you. He does this by lying about the strength of his hand through bluffing and discerning the times you attempt to bluff. Here's an example of how your stategy would play out. Let's say the following happens on the river.

You: Pair of 2's, check
Him: Ace-high, all-in

Now do you call or fold? You have the better hand here. If you knew what your opponent had you would definitely call. But since you are playing the odds, you decide to fold because you calculated you have a 30% of winning, which also means you have a 70% of losing. This is why playing the odds will cause you to lose. This is why it is the "psychological exercise" that the grandparent said it was.

Re:

[Propaganda13 (312548)]

psychology - the study of mind and behavior in relation to a particular field of knowledge or activity

Just because it's not about you wanting to have sex with your mom doesn't mean it's not psychology.

Pre-flop odds are all calculated on what your hand is. Statistically you know your chances on winning are. Your opponent's hand doesn't matter to you since it's unknown to you and doesn't factor into the odds.

Re:

[Brickwall (985910)]

I watch a lot of poker on TV, and I'm constantly amazed at how often Daniel Negrenau can call his opponent's hole cards correctly.

In a magazine profile, the writer played heads-up with Daniel for two hours. After the first half hour, Daniel was calling the writer's hole cards with astonishing accuracy.

You may not want to use the term psychology to describe this skill, but millions will disagree with you.

Re:Not harder than chess

[drfireman (101623)]

You tell yourself that. But it's BS. Poker, when it comes down to it, is all about a) statistics, and b) luck. Is there a psychological component to it? Sure. But I'll bet dollars to donuts those aspects are greatly outweighed by luck and a given player's ability to evaluate the statistics on a given hand.

One of the chief reasons there are winning poker players is that there are lots of players out there who are willing to bet dollars to donuts without knowing what they're talking about. There are experienced poker players who would agree with you. They're usually pretty bitter, because they can't understand why despite having learned the statistics and having played a large enough number of hands for their skill to win out, they're long-term losers to those of us who've taken the time to understand it better.

In limit games against unskilled opponents, you're right. In other games, the psychology is much more important. And in fact, if you want to do the probabilities right, you need the psychology. There's almost no hand of interest you can analyze properly without an estimate of some quantity like "the probability this bozo would make that raise in this situation." Is it statistical analysis or psychology? Is it the sugar or the stirring?

Re:

[Normal Dan (1053064)]

Far harder than chess. In chess, every permutation has a low number of values (every turn has few possible moves). In poker, every turn has a large number of possible moves/choices, such as how much to bet. Also, in chess, you can see the other players hand, in poker you cannot. This adds to the complication of poker. If this weren't bad enough, bluffing adds a whole new set of problems. Also, in chess, given enough computing power, you can process all the moves up until the end of the game. This is

Re:

[xero314 (722674)]

I thought the limit only applied to the maximum be

That would be spread limit as opposed to fixed limit which is what they were actually playing. Most flop/board/community poker games played around the world are fixed limit, though stud games tend toward spread limit.

Re:

[Otter (3800)]

In poker you have a finite number of cards, that are a lot smaller than the permutation of moves in chess or checkers.

First of all, moderators, this is mistaken, not "Flamebait".

Second, you're correct that the cards are trivial to calculate. The betting process in poker is what's much more difficult to model.

Watching it occasionally on ESPN, I see people who are presumably good enough to be on television doing things that are completely insane. (Why the hell would anyone go all-in with unsuited 8-3?!?) It

Re:Not harder than chess

[AuMatar (183847)]

Because there's more to a situation than your cards. There's your chip stack, your blinds, the action behind you, your opponents chip stacks, the payment structure, and your position. Pushing on 8-3 unsuited is a poor move, but there's at least two situations where it's called for- if you're far from a money boundary in the payment structure, have a small number of chips in compared to the blinds (say an M of 3-5), and all players before you folded. In this case, by pushing in you're likely to win the blinds. Especially if none of your remaining opponents have a big stack. The risk can be worth it, since it makes absolutely no difference what hand you go out on unless you reach a new money boundary, and you'll have to win at least 1 hand to do so. And with 83, you're likely to have 2 live cards if called by a high ace (AK, AQ, AJ, AT). Note that you'd only want to do this if first into the pot- someone who called the blind is too likely to call you for only an additional 2-4 big blinds.

The other situation to try it in is a squeeze play- if you have a raise and a call behind you, you have a very tight table image, and you think they don't have good hands. A raise, especially an all in raise, is signaling an extremely good hand. From a tight player, this must be respected. You can get both players to fold here if they don't have premium hands (AK, QQ-AA). This is a high risk move though, and you must have been playing extremely tight, versus people capable of laying down a good hand, to try it.

Re:

[Kjella (173770)]

(Why the hell would anyone go all-in with unsuited 8-3?!?)

Because when you're bluffing, you don't bluff half-way so they'll call you on it (as opposed to when you're not bluffing and want to fish for more chips), and if someone with a top hand decides to call you on it, your medium hand will probably lose anyway. So if you're looking to make the others fold, unsuited 8-3 is as good a bluff as any other hand. Besides, if you're in a squeeze and hit the right company you can still win and get back in the figh

Re:

[wildsurf (535389)]

It seems like the problem here might be the helplessness of artificial intelligence in the face of natural stupidity.

Douglas Adams invented a word for this:

ABOYNE (vb.) [langmaker.com] To beat an expert at a game of skill by playing so appallingly that none of his clever tactics or strategies are of any use to him.

Re:

[packeteer (566398)]

Your point is right but some of the things you say are a little off.

This is beyond simple mathematical calculations and hence it's MUCH harder than chess.
Chess is much more than just simple calculations. It is full of very complex calculations. Because of the incredibly huge number of moves possible it is more than just calculating. The best computer chess programs calculate less and use pattern recognition more. These days a computer with a fraction of the computing power of Deep Blue would beat it. T

yea well

[jimbug (1119529)]

let's see how well those computers do in strip poker!

Re:

[NeoTerra (986979)]

That all depends on if it has an internet connection or not ;)

Re:

[sa1lnr (669048)]

Mine has to play with a handicap. The side panel is already off.

Only expert players ....

[gstoddart (321705)]

I got the impression from some of the news stories that two professional poker players barely beat out the machine.

I have a sneaking suspicion that, for the vast majority of players, the computer is gonna kick your ass quite handily.

For the same reasons, I suspect that everyone who wasn't at the level of Kasparov would have gotten their asses handed to them in a game of chess against older versions of computers which couldn't yet beat him.

This, of course, begs the question of how long it will take for the on-line casinos to start putting poker playing bots into the mix to skew the odds even further to the house. I mean, if you have a computer program which will beat everyone else, why not just dial it down so it only wins 30% of the time or so and nobody will be any wiser.

Cheers

Re:

[CrazyJim1 (809850)]

I got the impression from some of the news stories that two professional poker players barely beat out the machine

In poker, professional players barely beat out amatuers nowadays.

My friend and I wrote an interesting poker program which sets up a table of 10 on a standard sit and go style table, and plays through 10,000 iterations to see which bot is the best.

Me, being the slacker, never made any bots to play his so it kinda fizzled out because I'm a bum... But it did have potential.

Re:

[Animats (122034)]

For the same reasons, I suspect that everyone who wasn't at the level of Kasparov would have gotten their asses handed to them in a game of chess against older versions of computers which couldn't yet beat him.

Current reality is that any of the better [wikipedia.org] chess programs [wikipedia.org] for PCs can trounce you, unless you've been on the cover of Chess Life. Grandmasters are now playing Rybka with Rybka handicapped by one pawn, or with no opening book, and still losing fairly often. It's clear that computer chess performa

Hang on a Minute...

[bateleur (814657)]

The implication here is that there is no (known) equilibrium mixed strategy for bluffs (because if there were then Polaris could be coded to use it).

Is that really true?! It seems very counterintuitive.

Certainly there's nothing special in general about games involving bluff. One of Von Neumann's first game theory case studies involved a simplified version of poker precisely to demonstrate how to automate bluffing.

Re:Hang on a Minute...

[Shaterri (253660)]

Simple bluffs are pretty straightforward to handle, but the combination of factors in poker (multiple rounds of action, shifting hand strength, complex unknown information) makes it inordinately difficult to compute Von Neumann optimal strategies. Even simpler games like (0,1) poker (both players are randomly 'dealt' a number in the 0..1 range, smallest number wins) with multiple betting rounds are remarkably difficult to solve under normal betting patterns. For more information, I heartily recommend The Mathematics of Poker by Chen and Ankenman.

Looks like it'll be this way. . .

[Astro HJX (1133429)]

I think that it'll probably stay this way for a while - man beats machine, altho as been talked about before when someone got beat in chess by one. I can't remember the name of it, but I'm sure others know. I'll be impressed once computers can out-think human beings totally.

probability

[ejito (700826)]

Seems like a computer's ability to compute probability should win in the long haul. Dealing with bluffing seems moot when you can compute cash flow stakes using something like a markov chain.

How far we've come.

[Rob T Firefly (844560)]

Dealer: My deal..
Eliza: What does that suggest to you?
Dealer: It suggests I'm giving you your cards.
Eliza: We can talk about me later. Now back to you...
Guest: Here you go.
Eliza: So you feel I go...
Guest: Um.. yeah. How many cards do you want?
Eliza: What else comes to mind when you ask that?
Dealer: You need to give me whatever cards you want to exchange.
Eliza: I see. Tell me more.
Dealer: Um.. so you can get a better hand?
Eliza: We were discussing you--not me.
Dealer: Do you have any interest in playing this game?
Eliza: Oh, I have any interest in playing this game?
Dealer: That's it, I quit! Go find someone else to torture!
Eliza: That would't help much, now, would it?

stratego, l'attaque, dover patrol, tri-tactics etc

[hedley (8715)]

Games with imperfect information. Very hard to design good AI to play these games, as the story says, tree search is not a win here. A game like stratego also has concepts that go beyond individual piece movement, i.e. you may want to group an few pieces together to make an attack, moving the unit (subject to input from the enemy) forwards. I have yet to see a good stratego game, there is one for $ called "The General". It can be defeated quite easily. I have found a stratego game in the past that could *not* be defeated! But, some sleuthing on my part (via saving the game and restoring it at key points) showed the sw was cheating by moving its pieces around to adjust to the threats(!). I have had an obsession with this style of AI but its such a daunting problem its hard to get a good handle on where to start to chip away at it. I suspect the polaris folks have been doing just this, the AI and methods they develop would be useful for other games I am sure.

H.

Environmental Sensors

[jshriverWVU (810740)]

Would be nifty if the bot's had access to environmental sensors like a camera so it could do facial recognition on the people to detect twitching, detect very little sweating, excess heat coming off body, things to interpret lying. Just an idea, and not *that* far fetched.

Re:

[gad_zuki! (70830)]

excess heat coming off body

No. They shouldnt be allowed to observe anything a person cant. I cant get up in the middle of a poker game and attempt to stick a thermometer into my opponent's rear to see if he's lying. Why not just put a camera behind him and read his cards? How do you propose we detect sweat? Measuring skin resistance? You cant do that in a real game either.

I think a plain-jane camera would be allowed, but even then its pretty unfair. The human player has no face to look at to potentiall

Limit Holdem

[venicebeach (702856)]

Keep in mind these bots play Limit hold'em, where the size of the bets is fixed. No-limit hold'em, the kind you typically see on tv is a much more complex problem - size of bets add more potentially misleading information and more choices to make. (that's why its more exciting to watch than limit)

Re:

[mosch (204)]

Well the main point I was making was about computational complexity.

And I think your point is dead false, especially when it comes to televised poker, in which the blinds are always very large, and the stacks quite short, meaning that the correct move is almost always mathematically provable, if one had the inclination.

If one was allowed, one could sit at the table with software like SNG Analyzer [sitngo-analyzer.com], enter the tournament structure, and assuming the player was capable of making decent estimates of people's rai

Re:

[venicebeach (702856)]

I'm not going to argue which is more exciting, since that is up to your personal preferences, although the evidence available to us is that NLHE has achieved a much larger audience than LHE.

About the computational issue you are actually incorrect here, and there is an objective fact of the matter. The reason most poker AI only attempts Heads Up Limit poker at this point is because there are more degrees of freedom in NLHE. At each decision point in a limit match the only options are bet, call, or fold

Well, in that case...

[Xeth (614132)]

I'd like to reaffirm my loyalty for this country and its human president. They may not be perfect but they're the best we've got. For now.

Humans Can Still Out-Bluff Machines

[Angostura (703910)]

That's what they want you to think.

Second day was not a fair competition

[dl248 (67452)]

Look at the first entry (bottom of page) on the Polaris team's blog for the second day. The day that the humans started winning:

http://www.cs.ualberta.ca/~games/poker/man-machine /Live/Day2Session1/ [ualberta.ca]

The U of A team gave the humans the logs of the first two games!

Perhaps after the entire match they could have reviewed the game logs, however this give the humans an unfair advantage during the second day. I can't believe that this isn't getting more attention -- they bascially gave the human team a huge insight into the inner workings, strategy, and tendencies of their opponent. Something that Polaris definitely did not have.

In my opinion this sours the competition and completely invalidates the final two matches. The human likely found a weakness (or two or three) and exploited it, and we can't know for sure that they would have found the weakness without those logs.

That was a huge mistake by the U of A team, and they have apparently got away with it without anyone noticing.

Re:

[Vegeta99 (219501)]

Why don't you think the computer had logs? I mean, Colin Powell says Iraq has WMDs, but that doesn't make it true!

Yes, I just invoked Godwin's Law Junior.

RTFA

[evanbd (210358)]

There were ten "bots"; which bot was in use was controlled by a "coach" program. They actually ran three different programs over the course of the tournament, and that setup actually lost to the humans. The coach / agent approach is an interesting one for a variety of reasons, and it is most definitely a valid strategy.

Re:That's cheating. The computer wasn't playing.

[by Anonymous Coward]

Let's see how well the computer does when IT makes all the decisions.

Their answer would be to turn it off and on again.

RTFA.

[raehl (609729)]

The researchers didn't choose which bots were used themselves - they had ANOTHER 'coach' bot that moved the 'player' bots in and out.

Re:RTFA.

[bogjobber (880402)]

You are also wrong. They chose the bots for the first two games, and the play was very close. They ran the 'coach' bot in the third game, and the computer got beaten "handily".

Re:RTFA.

[CyberLord Seven (525173)]

Think of it this way: the human player was playing against a "coach" who could vary his personality through the game.

why so wordy?

[Quadraginta (902985)]

/* Design for computer poker player.  Some implementation details missing. */

#include <stdio.h>
#include <poker.h>

int main() {

   printf("Hello, world.  I am a poker-playing robot.  Prepare to lose your shirt.\n") ;

   while (!win_poker_game()) {
      printf("Curses! Another game, human?"\n") ;
   } ;

   printf("Ha ha!\n") ;

   (void)rake_in_chips() ;

   return(0) ;
}