Deepstack Poker

Sung Joo Hyun has won the 2021 World Poker Tour DeepStacks $1,600 buy-in no-limit hold’em main event held at The Venetian® Resort Las Vegas. The South Korean defeated a field of 812 total entries to earn the title and the top prize of $208,335, the largest score of his career. Hyun had earned his first World Series of Poker gold bracelet just over half of a year earlier, coming out on top of a field of 2,307 entries in a $500 buy-in WSOP Online event to earn $161,898. He now has career tournament earnings of $699,320.

DeepStack Showdown Poker Tournament January 18–February 1, 2021. More than $1 Million in guaranteed prize pools. Deep Stack Poker & Card Room. 1/2NL cash table is running!! Tournament is running!! Come run your luck with us!!! 3814 Fishinger Blvd Hilliard, OH 43026 614-710-1616. DeepStack Showdown Poker Tournament March 1–28, 2021. More than $3.1 Million in guaranteed prize pools.

In addition to the title and the money, Hyun was also awarded 912 Card Player Player of the Year points as the champion of this event. This win alone was enough to catapult him into seventh place in the 2021 POY race standings, which are sponsored by Global Poker.

The sizable turnout for this event saw the $500,000 guarantee more than doubled, with $1,161,160 ultimately paid out among the top 102 finishers.

Plenty of notables made deep runs in this event, including WSOP bracelet winner Ronnie Bardah (92nd – $2,585), WSOP Circuit main event winner Michael Trivett (90th – $2,835), Javier Zarco (81st – $3,090), WPT Championship winner Asher Conniff (76th – $3,090), Card Player Poker Tour main event winner Oddie Dardon (43rd – $4,635), Aaron Massey (38th -$4,635), three-time WPT champion and two-time bracelet winner Anthony Zinno (37th – $4,635), WPT champion Joe Tehan (31st – $5,330), and a pair of WSOP bracelet winners Erik Cajelais (17th – $11,120) and Joey Weissman (11th – $16,920).

The final day of this event began with eight players remaining, with Wayne Harmon in the lead and Hyun sitting on the third-shortest stack. he quickly began to climb up the leaderboard, starting by eliminating Iris Angeleri in eighth place ($27,495). Joris Springael was the next to fall. His pocket tens couldn’t hold up against the A-3 of Curtis Powell and he was sent to the rail with $34,560 for his seventh-place showing. Hyun found a double-up through Powell not long after that to continue his ascent up the chip counts. Powell got the last of his chips in not long after that with two pair against the flush draw of Hyun. The draw came in and Powell was knocked out in sixth place ($41,765).

Hyun overtook the lead by winning a big pot off of Wayne Harmon with the nut flush against a lower flush. Harmon was left short, but managed to double up through WPT champion Dylan Wilkerson to regain his footing. He then busted Wilkerson in fifth place ($52,580), winning a race with pocket tens against the A-Q suited of the 2014 WPT Emperors Palace Poker Classic winner to send him packing.

Deep Stack Poker & Card Room. 1/2NL cash table is running!! Tournament is running!! Come run your luck with us!!! 3814 Fishinger Blvd Hilliard, OH 43026 614-710-1616. Feb 5, 2021, 7:28 PM. Deep Stack Poker & Card Room. Doors open at 12. Cash games all day, tournament tonight at. Dec 12, 2020 Essence of Deep Stack Poker Strategy. Deep stacks are defined as 200 BBs or more and the biggest change in game-play is you actually have to play the turn and river. If you're playing with 50-100 BB stacks, by the time you have a bet and a raise on the flop, if you're committed it's always going in either on the flop or the turn.

Chris Doan’s run in this event came to an end when his KJ came up against the A9 of Hyun. Doan failed to improve and was eliminated in fourth place ($69,025), while Hyun extended his lead heading into three-handed action. Roman Shainiuk closed the gap by busting Wayne Harmon in third place. It was a preflop race, with Shainiuk holding A8 and Harmon the 77. The board brought a flush for Shainiuk and Harmon had to settle for $93,280 as the third-place finisher.

With that Hyun took 13,310,000 into heads-up play against Shainiuk, who sat with 11,050,0000. Hyun was able to extend his lead to nearly a 4:1 advantage by the time the final hand was dealt. Shainiuk raised to 500,000 from the button with K6 and Hyun three-bet all-in holding KQ. Shainiuk called and the board came down Q923A. Hyun made a pair of queens to lock up the pot and the title, while Shainiuk took home $144,480 as the runner-up.

Here is a look at the payouts and POY points awarded at the final table:

Deep Stack Poker Tournaments

Winner photo credit: World Poker Tour.

Expert-Level Artificial Intelligence in Heads-Up No-Limit Poker

Links

Twitch | YouTube | Twitter
Downloads & Videos | Media Contact

DeepStack bridges the gap between AI techniques for games of perfect information—like checkers, chess and Go—with ones for imperfect information games–like poker–to reason while it plays using “intuition” honed through deep learning to reassess its strategy with each decision.

With a study completed in December 2016 and published in Science in March 2017, DeepStack became the first AI capable of beating professional poker players at heads-up no-limit Texas hold'em poker.

DeepStack computes a strategy based on the current state of the game for only the remainder of the hand, not maintaining one for the full game, which leads to lower overall exploitability.

DeepStack avoids reasoning about the full remaining game by substituting computation beyond a certain depth with a fast-approximate estimate. Automatically trained with deep learning, DeepStack's “intuition” gives a gut feeling of the value of holding any cards in any situation.

DeepStack considers a reduced number of actions, allowing it to play at conventional human speeds. The system re-solves games in under five seconds using a simple gaming laptop with an Nvidia GPU.

The first computer program to outplay human professionals at heads-up no-limit Hold'em poker

Deepstack Poker Blind Structure

In a study completed December 2016 and involving 44,000 hands of poker, DeepStack defeated 11 professional poker players with only one outside the margin of statistical significance. Over all games played, DeepStack won 49 big blinds/100 (always folding would only lose 75 bb/100), over four standard deviations from zero, making it the first computer program to beat professional poker players in heads-up no-limit Texas hold'em poker.

Games are serious business

Don’t let the name fool you, “games” of imperfect information provide a general mathematical model that describes how decision-makers interact. AI research has a long history of using parlour games to study these models, but attention has been focused primarily on perfect information games, like checkers, chess or go. Poker is the quintessential game of imperfect information, where you and your opponent hold information that each other doesn't have (your cards).

Until now, competitive AI approaches in imperfect information games have typically reasoned about the entire game, producing a complete strategy prior to play. However, to make this approach feasible in heads-up no-limit Texas hold’em—a game with vastly more unique situations than there are atoms in the universe—a simplified abstraction of the game is often needed.

A fundamentally different approach

DeepStack is the first theoretically sound application of heuristic search methods—which have been famously successful in games like checkers, chess, and Go—to imperfect information games.

At the heart of DeepStack is continual re-solving, a sound local strategy computation that only considers situations as they arise during play. This lets DeepStack avoid computing a complete strategy in advance, skirting the need for explicit abstraction.

During re-solving, DeepStack doesn’t need to reason about the entire remainder of the game because it substitutes computation beyond a certain depth with a fast approximate estimate, DeepStack’s 'intuition' – a gut feeling of the value of holding any possible private cards in any possible poker situation.

Finally, DeepStack’s intuition, much like human intuition, needs to be trained. We train it with deep learning using examples generated from random poker situations.

DeepStack is theoretically sound, produces strategies substantially more difficult to exploit than abstraction-based techniques and defeats professional poker players at heads-up no-limit poker with statistical significance.

Members (Front-back)

Michael Bowling, Dustin Morrill, Nolan Bard, Trevor Davis, Kevin Waugh, Michael Johanson, Viliam Lisý, Martin Schmid, Matej Moravčík, Neil Burch

low-variance Evaluation

Deepstack Poker Venetian

The performance of DeepStack and its opponents was evaluated using AIVAT, a provably unbiased low-variance technique based on carefully constructed control variates. Thanks to this technique, which gives an unbiased performance estimate with 85% reduction in standard deviation, we can show statistical significance in matches with as few as 3,000 games.

Abstraction-based Approaches

Despite using ideas from abstraction, DeepStack is fundamentally different from abstraction-based approaches, which compute and store a strategy prior to play. While DeepStack restricts the number of actions in its lookahead trees, it has no need for explicit abstraction as each re-solve starts from the actual public state, meaning DeepStack always perfectly understands the current situation.

Professional Matches

Las Vegas Poker Tournaments 2020

We evaluated DeepStack by playing it against a pool of professional poker players recruited by the International Federation of Poker. 44,852 games were played by 33 players from 17 countries. Eleven players completed the requested 3,000 games with DeepStack beating all but one by a statistically-significant margin. Over all games played, DeepStack outperformed players by over four standard deviations from zero.

Deepstack Poker Venetian

Heuristic Search

At a conceptual level, DeepStack’s continual re-solving, “intuitive” local search and sparse lookahead trees describe heuristic search, which is responsible for many AI successes in perfect information games. Until DeepStack, no theoretically sound application of heuristic search was known in imperfect information games.

Deepstack Poker Strategy