Tuesday, 16 July 2019
Latest news
Main » Facebook and CMU's poker AI beat five pros at once

Facebook and CMU's poker AI beat five pros at once

14 July 2019

This system is the only AI to have bettered professional poker players at this multi-player game. In a two-player game, it can be an effective strategy for AI - ideally, the human opponent will slip up or upset the equilibrium resulting in a win for the machine but at worst, the game will result in a tie.

Pluribus is innovated on Libratus, the AI that decisively beat four leading human professionals in the two-player variant of poker called heads-up no-limit Texas hold'em past year.

"It was incredibly fascinating getting to play against the poker bot and seeing some of the strategies it chose" Gagliano said.

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.

It was also able to keep its rivals guessing - playing wildly at times and conservatively at others. Designed by researchers from Facebook's AI lab and Carnegie Mellon, it played over 10,000 hands of poker against five pros-all of whom have won at least $1 million during their poker careers-winning a virtual $48,000. The AI had a very high win rate when it competed against five professional poker players in 10,000 hands of the game over 12 days. Bots were already dominant at two, or three-player poker, but six players is much harder.The feat represents a major breakthrough in artificial intelligence that could one day apply to far beyond card games to everything from cybersecurity to navigating self-driving cars.

According to the creators of Pluribus, the technology could be used to solve a "wide variety of real-world problems" that, like in poker, involve actors who bluff, or hide key information.

Once in a game with humans, Pluribus would keep looking ways to improve on that baseline, or "blueprint" strategy.

It then adopted the winning approach each time.

Pluribus also seeks to be unpredictable. After all, it wouldn't get very far if it saved its bets for excellent hands only.

The amount of time Pluribus takes to search on a single subgame varies between one second and 33 seconds depending on the particular situation.

Artificial Intelligence (AI) has once again approved that it is capable of matching up to what humans can do or even beating them at some of those things. It's a matter of execution for humans - to do this in a perfectly random way and to do so consistently. "I don't think many people will play online poker for a lot of money when they know that this type of software might be out there and people could use it to play against them for money". And it was amazingly cheap to train and operate, unlike some previous algorithmic champion players. As the scientists described it, "The AI starts from scratch by playing randomly, and gradually improves as it determines which actions, and which probability distribution over those actions, lead to better outcomes against earlier versions of its strategy".

ANNs can be trained to recognise patterns in information - including speech, text data, or visual images - and are the basis for a large number of the developments in AI over recent years.

Practical applications include Google's language translation services, Facebook's facial recognition software and Snapchat's image altering live filters.

A new breed of ANNs called Adversarial Neural Networks pits the wits of two AI bots against each other, which allows them to learn from each other.

Facebook and CMU's poker AI beat five pros at once