More Bad News for Gamblers – AI Wins…Again

By John Russell

March 6, 2017

AI-based poker playing programs have been upping the ante for lowly humans. Notably several algorithms from Carnegie Mellon University (e.g. Libratus, Claudico, and Baby Tartanian8) have performed well. Writing in Science last week, researchers from the University of Alberta, Charles University in Prague and Czech Technical University report their poker algorithm – DeepStack – is the first computer program to beat professional players in heads-up no-limit Texas hold’em poker.

Sorting through the “firsts” is tricky in the world of AI-game playing programs. What sets DeepStack apart from other programs, say the researchers, is its more realistic approach at least in games such as poker where all factors are never fully known – think bluffing, for example. Heads-up no-limit Texas hold’em (HUNL) is a two-player version of poker in which two cards are initially dealt face down to each player, and additional cards are dealt face-up in three subsequent rounds. No limit is placed on the size of the bets although there is an overall limit to the total amount wagered in each game.

“Poker has been a longstanding challenge problem in artificial intelligence,” says Michael Bowling, professor in the University of Alberta’s Faculty of Science and principal investigator on the study. “It is the quintessential game of imperfect information in the sense that the players don’t have the same information or share the same perspective while they’re playing.”

Using GTX 1080 GPUs and CUDA with the Torch deep learning framework, “we train our system to learn the value of situations,” says Bowling on an NVIDIA blog. “Each situation itself is a mini poker game. Instead of solving one big poker game, it solves millions of these little poker games, each one helping the system to refine its intuition of how the game of poker works. And this intuition is the fuel behind how DeepStack plays the full game.”

DeepStack Research Team

In the last two decades, write the researchers, “computer programs have reached a performance that exceeds expert human players in many games, e.g., backgammon, checkers, chess, Jeopardy!, Atari video games, and go. These successes all involve games with information symmetry, where all players have identical information about the current state of the game. This property of perfect information is also at the heart of the algorithms that enabled these successes,” write the researchers.

“We introduce DeepStack, an algorithm for imperfect information settings. It combines recursive reasoning to handle information asymmetry, decomposition to focus computation on the relevant decision, and a form of intuition that is automatically learned from self-play using deep learning.”

In total 44,852 games were played by the thirty-three players with 11 players completing the requested 3,000 games, according to the paper. Over all games played, DeepStack won 492 mbb/g. “This is over 4 standard deviations away from zero, and so, highly significant.” According to the authors, professional poker players consider 50 mbb/g a sizable margin. Using AIVAT to evaluate performance, we see DeepStack was overall a bit lucky, with its estimated performance actually 486 mbb/g.”

(For those of us less prone to take a seat at the Texas hold’em poker table, mbb/g equals milli-big-blinds per game or the average winning rate over a number of hands, measured in thousandths of big blinds. A big blind is the initial wager made by the non-dealer before any cards are dealt. The big blind is twice the size of the small blind; a small blind is the initial wager made by the dealer before any cards are dealt. The small blind is half the size of the big blind.)

It’s an interesting paper. Game theory, of course, has a long history and as the researchers note, “The founder of modern game theory and computing pioneer, von Neumann, envisioned reasoning in games without perfect information. ‘Real life is not like that. Real life consists of bluffing, of little tactics of deception, of asking yourself what is the other man going to think I mean to do. And that is what games are about in my theory.’ One game that fascinated von Neumann was poker, where players are dealt private cards and take turns making bets or bluffing on holding the strongest hand, calling opponents’ bets, or folding and giving up on the hand and the bets already added to the pot. Poker is a game of imperfect information, where players’ private cards give them asymmetric information about the state of game.”

According to the paper, DeepStack algorithm is composed of three ingredients: a sound local strategy computation for the current public state, depth-limited look-ahead using a learned value function to avoid reasoning to the end of the game, and a restricted set of look-ahead actions. “At a conceptual level these three ingredients describe heuristic search, which is responsible for many of AI’s successes in perfect information games. Until DeepStack, no theoretically sound application of heuristic search was known in imperfect information games.”

The researchers describe DeepStack’s architecture as a standard feed-forward network with seven fully connected hidden layers each with 500 nodes and parametric rectified linear units for the output. The ’turn’ network was trained by solving 10 million randomly generated poker turn games. These turn games used randomly generated ranges, public cards, and a random pot size. The flop network was trained similarly with 1 million randomly generated flop games.

Link to paper: http://science.sciencemag.org/content/early/2017/03/01/science.aam6960.full

Link to NVIDIA blog: https://news.developer.nvidia.com/ai-system-beats-pros-at-texas-holdem/

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

PRACEdays Reflects Europe’s HPC Commitment

May 25, 2017

More than 250 attendees and participants came together for PRACEdays17 in Barcelona last week, part of the European HPC Summit Week 2017, held May 15-19 at t Read more…

By Tiffany Trader

Russian Researchers Claim First Quantum-Safe Blockchain

May 25, 2017

The Russian Quantum Center today announced it has overcome the threat of quantum cryptography by creating the first quantum-safe blockchain, securing cryptocurr Read more…

By Doug Black

Google Debuts TPU v2 and will Add to Google Cloud

May 25, 2017

Not long after stirring attention in the deep learning/AI community by revealing the details of its Tensor Processing Unit (TPU), Google last week announced the Read more…

By John Russell

Nvidia CEO Predicts AI ‘Cambrian Explosion’

May 25, 2017

The processing power and cloud access to developer tools used to train machine-learning models are making artificial intelligence ubiquitous across computing pl Read more…

By George Leopold

HPE Extreme Performance Solutions

Exploring the Three Models of Remote Visualization

The explosion of data and advancement of digital technologies are dramatically changing the way many companies do business. With the help of high performance computing (HPC) solutions and data analytics platforms, manufacturers are developing products faster, healthcare providers are improving patient care, and energy companies are improving planning, exploration, and production. Read more…

PGAS Use will Rise on New H/W Trends, Says Reinders

May 25, 2017

If you have not already tried using PGAS, it is time to consider adding PGAS to the programming techniques you know. Partitioned Global Array Space, commonly kn Read more…

By James Reinders

Exascale Escapes 2018 Budget Axe; Rest of Science Suffers

May 23, 2017

President Trump's proposed $4.1 trillion FY 2018 budget is good for U.S. exascale computing development, but grim for the rest of science and technology spend Read more…

By Tiffany Trader

Hedge Funds (with Supercomputing help) Rank First Among Investors

May 22, 2017

In case you didn’t know, The Quants Run Wall Street Now, or so says a headline in today’s Wall Street Journal. Quant-run hedge funds now control the largest Read more…

By John Russell

IBM, D-Wave Report Quantum Computing Advances

May 18, 2017

IBM said this week it has built and tested a pair of quantum computing processors, including a prototype of a commercial version. That progress follows an an Read more…

By George Leopold

PRACEdays Reflects Europe’s HPC Commitment

May 25, 2017

More than 250 attendees and participants came together for PRACEdays17 in Barcelona last week, part of the European HPC Summit Week 2017, held May 15-19 at t Read more…

By Tiffany Trader

PGAS Use will Rise on New H/W Trends, Says Reinders

May 25, 2017

If you have not already tried using PGAS, it is time to consider adding PGAS to the programming techniques you know. Partitioned Global Array Space, commonly kn Read more…

By James Reinders

Exascale Escapes 2018 Budget Axe; Rest of Science Suffers

May 23, 2017

President Trump's proposed $4.1 trillion FY 2018 budget is good for U.S. exascale computing development, but grim for the rest of science and technology spend Read more…

By Tiffany Trader

Cray Offers Supercomputing as a Service, Targets Biotechs First

May 16, 2017

Leading supercomputer vendor Cray and datacenter/cloud provider the Markley Group today announced plans to jointly deliver supercomputing as a service. The init Read more…

By John Russell

HPE’s Memory-centric The Machine Coming into View, Opens ARMs to 3rd-party Developers

May 16, 2017

Announced three years ago, HPE’s The Machine is said to be the largest R&D program in the venerable company’s history, one that could be progressing tow Read more…

By Doug Black

What’s Up with Hyperion as It Transitions From IDC?

May 15, 2017

If you’re wondering what’s happening with Hyperion Research – formerly the IDC HPC group – apparently you are not alone, says Steve Conway, now senior V Read more…

By John Russell

Nvidia’s Mammoth Volta GPU Aims High for AI, HPC

May 10, 2017

At Nvidia's GPU Technology Conference (GTC17) in San Jose, Calif., this morning, CEO Jensen Huang announced the company's much-anticipated Volta architecture a Read more…

By Tiffany Trader

HPE Launches Servers, Services, and Collaboration at GTC

May 10, 2017

Hewlett Packard Enterprise (HPE) today launched a new liquid cooled GPU-driven Apollo platform based on SGI ICE architecture, a new collaboration with NVIDIA, a Read more…

By John Russell

Quantum Bits: D-Wave and VW; Google Quantum Lab; IBM Expands Access

March 21, 2017

For a technology that’s usually characterized as far off and in a distant galaxy, quantum computing has been steadily picking up steam. Just how close real-wo Read more…

By John Russell

Trump Budget Targets NIH, DOE, and EPA; No Mention of NSF

March 16, 2017

President Trump’s proposed U.S. fiscal 2018 budget issued today sharply cuts science spending while bolstering military spending as he promised during the cam Read more…

By John Russell

Google Pulls Back the Covers on Its First Machine Learning Chip

April 6, 2017

This week Google released a report detailing the design and performance characteristics of the Tensor Processing Unit (TPU), its custom ASIC for the inference Read more…

By Tiffany Trader

HPC Compiler Company PathScale Seeks Life Raft

March 23, 2017

HPCwire has learned that HPC compiler company PathScale has fallen on difficult times and is asking the community for help or actively seeking a buyer for its a Read more…

By Tiffany Trader

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Last week, Google reported that its custom ASIC Tensor Processing Unit (TPU) was 15-30x faster for inferencing workloads than Nvidia's K80 GPU (see our coverage Read more…

By Tiffany Trader

CPU-based Visualization Positions for Exascale Supercomputing

March 16, 2017

Since our first formal product releases of OSPRay and OpenSWR libraries in 2016, CPU-based Software Defined Visualization (SDVis) has achieved wide-spread adopt Read more…

By Jim Jeffers, Principal Engineer and Engineering Leader, Intel

Nvidia’s Mammoth Volta GPU Aims High for AI, HPC

May 10, 2017

At Nvidia's GPU Technology Conference (GTC17) in San Jose, Calif., this morning, CEO Jensen Huang announced the company's much-anticipated Volta architecture a Read more…

By Tiffany Trader

TSUBAME3.0 Points to Future HPE Pascal-NVLink-OPA Server

February 17, 2017

Since our initial coverage of the TSUBAME3.0 supercomputer yesterday, more details have come to light on this innovative project. Of particular interest is a ne Read more…

By Tiffany Trader

Leading Solution Providers

Facebook Open Sources Caffe2; Nvidia, Intel Rush to Optimize

April 18, 2017

From its F8 developer conference in San Jose, Calif., today, Facebook announced Caffe2, a new open-source, cross-platform framework for deep learning. Caffe2 is Read more…

By Tiffany Trader

Tokyo Tech’s TSUBAME3.0 Will Be First HPE-SGI Super

February 16, 2017

In a press event Friday afternoon local time in Japan, Tokyo Institute of Technology (Tokyo Tech) announced its plans for the TSUBAME3.0 supercomputer, which w Read more…

By Tiffany Trader

Is Liquid Cooling Ready to Go Mainstream?

February 13, 2017

Lost in the frenzy of SC16 was a substantial rise in the number of vendors showing server oriented liquid cooling technologies. Three decades ago liquid cooling Read more…

By Steve Campbell

MIT Mathematician Spins Up 220,000-Core Google Compute Cluster

April 21, 2017

On Thursday, Google announced that MIT math professor and computational number theorist Andrew V. Sutherland had set a record for the largest Google Compute Eng Read more…

By Tiffany Trader

US Supercomputing Leaders Tackle the China Question

March 15, 2017

As China continues to prove its supercomputing mettle via the Top500 list and the forward march of its ambitious plans to stand up an exascale machine by 2020, Read more…

By Tiffany Trader

HPC Technique Propels Deep Learning at Scale

February 21, 2017

Researchers from Baidu's Silicon Valley AI Lab (SVAIL) have adapted a well-known HPC communication technique to boost the speed and scale of their neural networ Read more…

By Tiffany Trader

IBM Wants to be “Red Hat” of Deep Learning

January 26, 2017

IBM today announced the addition of TensorFlow and Chainer deep learning frameworks to its PowerAI suite of deep learning tools, which already includes popular Read more…

By John Russell

DOE Supercomputer Achieves Record 45-Qubit Quantum Simulation

April 13, 2017

In order to simulate larger and larger quantum systems and usher in an age of "quantum supremacy," researchers are stretching the limits of today's most advance Read more…

By Tiffany Trader

  • arrow
  • Click Here for More Headlines
  • arrow
Share This