Back to Table of contents

Primeur weekly 2018-01-08

Crowd computing

GIMPS Project discovers largest known prime number ...

Focus on Europe

OpenAIRE datathon encouraging developers and data scientists to analyse the OpenAIRE Information Space ...

HPC User Forum to be hosted at Teratec in March 2018 ...

Overview of European HPC research ...

ERC grantee behind discovery of major hardware bugs ...

University of Paderborn full member of the Gauss Alliance e.V. ...

Bulgarian Presidency of the Council of the EU to host Flagship Conference "Research Infrastructures beyond 2020 - sustainable and effective ecosystem for science and society" ...

ICRI 2018 to be hosted in Vienna, Austria in September 2018 ...

Hardware

Samsung now mass producing industry's first 2nd-generation, 10-nanometer class DRAM ...

India's first multi-petaflops supercomputer to be inaugurated at the Indian Institute of Tropical Meteorology ...

Cray appoints Catriona Fallon to Board of Directors ...

Unhackable computer under development with $3.6 million DARPA grant ...

Mellanox ships BlueField system-on-chip platforms and SmartNIC adapters to leading OEMs and hyperscale customers ...

Applications

Carnegie Mellon reveals inner workings of victorious AI ...

Registration of ASC18 Student Supercomputer Challenge now open ...

SUTD researchers discover a Valleytronics route towards reversible computer ...

Computer science pioneer Bjarne Stroustrup to receive the 2018 Charles Draper Prize for Engineeering ...

Conference on Neural Information Processing Systems hosted the conversational intelligence challenge finals ...

A simplified formulation of lattice gauge theories for applications in particle physics as well as quantum simulations ...

ASC18 competition timeline released, setting the stage for AI computing challenge ...

Tailoring cancer treatments to individual patients ...

The Cloud

Intersect360 Research report shows Huawei emerging as a global leader in HPC market with Cloud and AI convergence solutions ...

Microsoft to acquire Avere Systems, accelerating high-performance computing innovation for media and entertainment industry and beyond ...

Cyfronet to host 4th edition of Workshop on Cloud Services for Synchronisation and Sharing ...

Gridsum and Peking University Law School establish legal AI Lab and Research Institute ...

Carnegie Mellon reveals inner workings of victorious AI

Jason Les, a professional poker player specializing in heads-up, no-limit Texas Hold'em, is watched by Tuomas Sandholm, professor of computer science at Carnegie Mellon University, as play gets underway in the Brains Vs. AI competition in January 2017. Libratus, an AI developed at Carnegie Mellon, beat Les and three other pros during the 20-day competition in Pittsburgh. Credit: Carnegie Mellon University.17 Dec 2017 Pittsburgh - Libratus, an artificial intelligence that defeated four top professional poker players in no-limit Texas Hold'em earlier this year, uses a three-pronged approach to master a game with more decision points than atoms in the universe, researchers at Carnegie Mellon University reported.

In a paper published online by the journalScience, Tuomas Sandholm, professor of computer science, and Noam Brown, a Ph.D. student in the Computer Science Department, detail how their AI achieved superhuman performance by breaking the game into computationally manageable parts and, based on its opponents' game play, fix potential weaknesses in its strategy during the competition.

AI programmes have defeated top humans in checkers, chess and Go - all challenging games, but ones in which both players know the exact state of the game at all times. Poker players, by contrast, contend with hidden information: what cards their opponents hold and whether an opponent is bluffing.

In a 20-day competition involving 120,000 hands at Rivers Casino in Pittsburgh this past January, Libratus became the first AI to defeat top human players at Head's-Up, No-Limit Texas Hold'em - the primary benchmark and longstanding challenge problem for imperfect-information game-solving by AIs.

Libratus beat each of the players individually in the two-player game and collectively amassed more than $1.8 million in chips. Measured in milli-big blinds per hand (mbb/hand), a standard used by imperfect-information game AI researchers, Libratus decisively defeated the humans by 147 mmb/hand. In poker lingo, this is 14.7 big blinds per game.

"The techniques in Libratus do not use expert domain knowledge or human data and are not specific to poker", Tuomas Sandholm and Noam Brown said in the paper. "Thus, they apply to a host of imperfect-information games." Such hidden information is ubiquitous in real-world strategic interactions, they noted, including business negotiation, cybersecurity, finance, strategic pricing and military applications.

Libratus includes three main modules, the first of which computes an abstraction of the game that is smaller and easier to solve than by considering all 10161- the number 1 followed by 161 zeroes - possible decision points in the game. It then creates its own detailed strategy for the early rounds of Texas Hold'em and a coarse strategy for the later rounds. This strategy is called the blueprint strategy.

One example of these abstractions in poker is grouping similar hands together and treating them identically.

"Intuitively, there is little difference between a king-high flush and a queen-high flush", Noam Brown stated. "Treating those hands as identical reduces the complexity of the game and, thus, makes it computationally easier." In the same vein, similar bet sizes also can be grouped together.

But in the final rounds of the game, a second module constructs a new, finer-grained abstraction based on the state of play. It also computes a strategy for this subgame in real-time that balances strategies across different subgames using the blueprint strategy for guidance - something that needs to be done to achieve safe subgame solving. During the January competition, Libratus performed this computation using the Pittsburgh Supercomputing Center's Bridges computer.

When an opponent makes a move that is not in the abstraction, the module computes a solution to this subgame that includes the opponent's move. Tuomas Sandholm and Noam Brown call this nested subgame solving. DeepStack, an AI created by the University of Alberta to play Heads-Up, No-Limit Texas Hold'em, also includes a similar algorithm, called continual re-solving. DeepStack has yet to be tested against top professional players, however.

The third module is designed to improve the blueprint strategy as competition proceeds. Typically, Tuomas Sandholm said, AIs use machine learning to find mistakes in the opponent's strategy and exploit them. But that also opens the AI to exploitation if the opponent shifts strategy. Instead, Libratus' self-improver module analyzes opponents' bet sizes to detect potential holes in Libratus' blueprint strategy. Libratus then adds these missing decision branches, computes strategies for them, and adds them to the blueprint.

In addition to beating the human pros, Libratus was evaluated against the best prior poker AIs. These included Baby Tartanian8, a bot developed by Tuomas Sandholm and Noam Brown that won the 2016 Annual Computer Poker Competition held in conjunction with the Association for the Advancement of Artificial Intelligence Annual Conference. Whereas Baby Tartanian8 beat the next two strongest AIs in the competition by 12 (plus/minus 10) mbb/hand and 24 (plus/minus 20) mbb/hand, Libratus bested Baby Tartanian8 by 63 (plus/minus 28) mbb/hand. DeepStack has not been tested against other AIs, the authors noted.

"The techniques that we developed are largely domain independent and can thus be applied to other strategic imperfect-information interactions, including nonrecreational applications", Tuomas Sandholm and Noam Brown concluded. "Due to the ubiquity of hidden information in real-world strategic interactions, we believe the paradigm introduced in Libratus will be critical to the future growth and widespread application of AI."

The technology has been exclusively licensed to Strategic Machine Inc., a company founded by Tuomas Sandholm to apply strategic reasoning technologies to many different applications.

A paper by Noam Brown and Tuomas Sandholm regarding nested subgame solving recently won a Best Paper award at the Neural Information Processing Systems (NIPS 2017) conference. The National Science Foundation and the Army Research Office supported this research.
Source: Carnegie Mellon University - CMU

Back to Table of contents

Primeur weekly 2018-01-08

Crowd computing

GIMPS Project discovers largest known prime number ...

Focus on Europe

OpenAIRE datathon encouraging developers and data scientists to analyse the OpenAIRE Information Space ...

HPC User Forum to be hosted at Teratec in March 2018 ...

Overview of European HPC research ...

ERC grantee behind discovery of major hardware bugs ...

University of Paderborn full member of the Gauss Alliance e.V. ...

Bulgarian Presidency of the Council of the EU to host Flagship Conference "Research Infrastructures beyond 2020 - sustainable and effective ecosystem for science and society" ...

ICRI 2018 to be hosted in Vienna, Austria in September 2018 ...

Hardware

Samsung now mass producing industry's first 2nd-generation, 10-nanometer class DRAM ...

India's first multi-petaflops supercomputer to be inaugurated at the Indian Institute of Tropical Meteorology ...

Cray appoints Catriona Fallon to Board of Directors ...

Unhackable computer under development with $3.6 million DARPA grant ...

Mellanox ships BlueField system-on-chip platforms and SmartNIC adapters to leading OEMs and hyperscale customers ...

Applications

Carnegie Mellon reveals inner workings of victorious AI ...

Registration of ASC18 Student Supercomputer Challenge now open ...

SUTD researchers discover a Valleytronics route towards reversible computer ...

Computer science pioneer Bjarne Stroustrup to receive the 2018 Charles Draper Prize for Engineeering ...

Conference on Neural Information Processing Systems hosted the conversational intelligence challenge finals ...

A simplified formulation of lattice gauge theories for applications in particle physics as well as quantum simulations ...

ASC18 competition timeline released, setting the stage for AI computing challenge ...

Tailoring cancer treatments to individual patients ...

The Cloud

Intersect360 Research report shows Huawei emerging as a global leader in HPC market with Cloud and AI convergence solutions ...

Microsoft to acquire Avere Systems, accelerating high-performance computing innovation for media and entertainment industry and beyond ...

Cyfronet to host 4th edition of Workshop on Cloud Services for Synchronisation and Sharing ...

Gridsum and Peking University Law School establish legal AI Lab and Research Institute ...