On 31st January 2017, it was reported that a supercomputer running
software developed at Carnegie Mellon University had won the
“Brains vs. Artificial Intelligence” heads-up, no-limit Texas Hold'em
tournament playing against four human poker pros. It won
by US $1,766,250 in chips over 120,000 hands.
Decades ago I saw a cartoon depicting two guys sitting at a bar
and one guy, looking depressed, was saying to the other,
"I could understand if I had been made redundant by an entire
computer, but I have been replaced by a single transistor".
Well the news today isn't quite that bad for human poker players,
but a new Texas Hold'em AI called DeepStack has emerged with
a fresh victory running on nothing more than the type of GPU chip
found in a home gaming desktop computer.
Quote:
|
Originally Posted by Jeremy Hsu, IEEE Spectrum
DeepStack proved its poker-playing prowess in 44,852 games played against 33 poker pros recruited by the International Federation of Poker from 17 countries. Typically researchers would need to have their computer algorithms play a huge number of poker hands to ensure that the results are statistically significant and not simply due to chance. But the DeepStack team used a low-variance technique called AIVAT that filters out much of the chance factor and enabled them to come up with statistically significant results with as few as 3,000 games.
“We have a history in group of doing variance reduction techniques,” Bowling explains. “This new technique was pioneered in our work to help separate skill and luck.”
Of all the players, 11 poker pros completed the requested 3,000 games over a period of four weeks from November 7 to December 12, 2016. DeepStack handily beat 10 of the 11 with a statistically significant victory margin, and still technically beat the 11th player.
|
Quote:
|
Originally Posted by Jeremy Hsu, IEEE Spectrum
Worried poker fans may have even greater cause for concern with the success of DeepStack. Unlike Libratus, DeepStack’s remarkably effective forward-looking intuition means it does not have to do any extra computing beforehand. Instead, it always looks forward by solving for actual possible plays several moves ahead and then relies on its intuition to approximate the rest of the game.
This “continual re-solving” approach that can take place at any given point in a game is a step beyond the “endgame solver” that Libratus used only during the last betting rounds of each game. And the fact that DeepStack’s approach works on the hardware equivalent of a gaming laptop could mean the world will see the rise of many more capable AI bots tackling a wide variety of challenges beyond poker in the near future.
|
Article at the Institute of Electrical and Electronic Engineers (IEEE) here -
http://spectrum.ieee.org/automaton/r...emolish-humans