Facebook AI Pluribus Defeats Top Poker Pros In 6-Player Texas Hold 'Em

Carnegie Mellon University and Facebook AI research scientists have developed an AI dubbed Pluribus that took on 15 professional human players in six-player no-limit Texas Hold 'em and won. The researchers describe how they achieved this feat in a new paper in Science. Ars Technica reports: Playing more than 5,000 hands each time, five copies of the AI took on two top professional players: Chris "Jesus" Ferguson, six-time winner of World Series of Poker events, and Darren Elias, who currently holds the record for most World Poker Tour titles. Pluribus defeated them both. It did the same in a second experiment, in which Pluribus played five pros at a time, from a pool of 13 human players, for 10,000 hands.

Co-author Tuomas Sandholm of Carnegie Mellon University has been grappling with the unique challenges poker poses for AI for the last 16 years. No-Limit Texas Hold 'em is a so-called "imperfect information" game, since there are hidden cards (held by one's opponents in the hand) and no restrictions on the size of the bet one can make. By contrast, with chess and Go, the status of the playing board and all the pieces are known by all the players. Poker players can (and do) bluff on occasion, so it's also a game of misleading information.

Pluribus vs. Watson

[bobthesungeek76036]

That's what I want to see!!!

on line poker is not the same as live tables

[Joe_Dragon]

on line poker is not the same as live tables Where bluffing / tells are an bigger deal.

Re:

[mmdurrant]

Bluffing is completely unrelated to how the player physically interacts with the game.

An Excellent, readable, technical paper

[aberglas]

I encourage others to actually read it.

Basically, it plays against itself many times. But it can also see what its other selves would have done if it had played differently. Then sees how the play turned out and feeds that back.

To do that it simplifies its internal game somewhat. A few bet types, a few hand strengths, so the combinatorial explosion is manageable.

There is also a small amount of search involved.

Obviously no tells etc. But professional players have those well under control anyway.

One idea was that, for example, in sizzor-paper-rock an optimal strategy is to chose randomly. No opponent can beat that. Although given a human opponent there might be a better strategy involving second guessing. But just sticking to random will never be beaten any human, although it might not win either.

Re:

[AmiMoJo]

Bots have already ruined online poker. Players use them to calculate odds and count cards. If you join an online game these days you can be fairly sure you will be playing against people using bots, and unless you do too you are going to lose.

It's basically become bot players farming noobs who haven't figured out why they are losing yet.

Re:

[mmdurrant]

For the last time, CARD COUNTING IS NOT A THING IN POKER. Stupid slashdot filter .Here's some lowercase characters to fix your stupid percentage calculation.

Re:

[account_deleted]

Comment removed based on user account deletion

Really?

[OYAHHH]

A computer that has a infinite ability to count cards wins at cards? Hard to believe it isn't it?

Re: Really?

[Anonymous Coward]

Just think, some day the average computer will be as small as the family automobile!

Re:

[Anonymous Coward]

Counting cards has nothing to do with poker, so that concept is completely irrelevant here.

Re:

[Rockoon]

Found the low I.D. slashdotter that doenst know the difference between poker and blackjack. How the hell have you lived so many years and not figured out that there is a difference... its baffling, really.

Re:

[account_deleted]

Comment removed based on user account deletion

Re:

[mmdurrant]

I guarantee you're not going to win not knowing the rules of the game.

The ultimate point is....

[3seas]

games like poker are no more

Re:

[Tony Isaac]

I don't think so. The bots in this story were trained only against really good poker players. Less skilled players tend to be more erratic in their bluffs, and just might throw these bots for a loop.

Also, human players have an amazing ability to adapt. I'm not at all sure the bots will be able to hold their edge.

facebook poker app

[Bramlet Abercrombie]

I guess we'll be losing our libra and bitcoin to facebook's AI in a few years. They'll probably start lobbying to change gambling laws soon.

Emotions

[fluffernutter]

Human emotions are very important in high level poker. Hard to beat a player that doesn't have any, that's why you can't take certain drugs when playing.

I don't know why they keep doing this

[Sqreater]

This is about as interesting as a marathon between an human and an automobile - and it proves about as much. Human competition is interesting because it is human.

Re:

[Tony Isaac]

If it were so easy for a computer to win, why is this a story only now, decades after chess computers were able to beat the best humans?

Misinformation

[zymurgeek]

This is Facebook software that's good at creating misinformation. That sounds like it might come in handy.

Given this is a Facebook project...

[alispguru]

One easy way to win games like this is to cheat - let the bot players share information about their cards through channels the human players can't access.

These researchers work for the same company that did research on their users, seeing if they could change user's moods by putting up/downbeat stories in their news feed [theatlantic.com]. They openly published that.

Given that this is a Facebook project, they need to assure us they did not cheat.

Very limited test

[Tony Isaac]

These bots were trained against just a few expert players. Less skilled players tend to bluff erratically, and may confound these bots. Also, human players can learn to adapt. AND this is just six-player Texas Hold'Em. It's a lot harder to win in a bigger tournament.