AI programme beats pros in six-player poker

An AI Developed by Facebook and Carnegie Mellon Beats Champions of Poker

An AI Developed by Facebook and Carnegie Mellon Beats Champions of Poker

So far, developing an AI system capable of defeating elite players in full-scale poker with multiple opponents at the table was widely recognized as the key remaining milestone. A research paper about Pluribus was published Thursday in the journal Science. Pluribus - so-named because it takes on many opponents at once - learns by playing against itself over and over and remembering which strategies worked best.

Pluribus registered a solid win with statistical significance, which is particularly impressive given its opposition, Elias said. Inching towards that very aim, Facebook's AI Research team, in collaboration with Carnegie Mellon University (CMU), has developed an AI that can beat Pro Poker Players.

Apart from Pluribus, there are other AI as well that have gained mastery over zero-sum games such as checkers, chess, Go, two-player poker, StarCraft 2, and Dota 2.

And unlike in chess or Go, the computer does not have access to all the information available as it can not see its opponent's cards.

Artificial intelligence has already surpassed humans at games such as chess and Go, but in these games players can see the positions of all of the pieces; there is no information that is hidden from them.

Blinds were $50/$100 and each player began with 100 big blinds, so Pluribus averaged a $48,000 profit per game with just $60,000 on the table. Pluribus also became a good bluffer, with its opponents praising its relentless consistency.

"Strategies are much harder to compute outside of two-player zero-sum games", explained Sandholm.

In fact, one of Sandholm's companies, a startup called Strategy Robot that aims to come up with government applications for his AI game-playing work, already has a contract worth as much as $10 million with the U.S. military. For a start, Pluribus has an online search algorithm to look for ahead for options. The pair also carefully designed Pluribus to predict its opponents next couple moves-a strategy that gave the AI an edge without forcing it to calculate every possibility through the end of the game, which would have quickly gotten computationally expensive.

Would you let an Amazon robot into your house?
Amazon is inching closer to making a wheeled robotic assistant that can be controlled via its Echo smart speakers . Other companies have attempted to release voice-enabled robots in the past, but few have seen mainstream success.

Pluribus registered a solid win, and Mr Elias said 'The bot wasn't just playing against some middle of the road pros. Limping means making the smallest bet possible to stay in the hand, instead of raising or folding. Other AIs that have achieved significant milestones in games, such as DeepMind, have typically used large numbers of servers and farms of GPUs. After eight days, it had devised a "blueprint strategy", which it uses for the first round of betting.

Sandholm has founded two companies, Strategic Machine Inc. and Strategy Robot Inc., that have exclusively licensed strategic reasoning technologies developed in his Carnegie Mellon laboratory over the last 16 years.

Conversely, a part of the unusual strategies of the AI included the so-called practice of donk betting whereby the AI purposefully called one hand, but raised the one right after it.

A round of Texas hold'em in which the AI program Pluribus competed. However, given how devastating Facebook's Pluribus AI can be at the poker table, these players may want to reassess the validity of their accusations. For any other type of usage, the parties have agreed that they can use the additional code as they wish.

Brown, a research scientist at Facebook AI, is a Ph.D. student in Carnegie's Computer Science Department.

Pluribus training cost is the equivalent of less than $150 worth of cloud computing resources compared to other recent AI milestone projects, which required the equivalent of millions of dollars' worth of computing resources to train. With funds provided by Facebook, Elias and Ferguson were each paid $2,000 for their participation in the experiment, and Ferguson received an extra $2,000 for outperforming Elias.

Time and again, Pluribus prevailed against a randomly drawn player or players from this pool of killers.

Recommended News

We are pleased to provide this opportunity to share information, experiences and observations about what's in the news.
Some of the comments may be reprinted elsewhere in the site or in the newspaper.
Thank you for taking the time to offer your thoughts.