Back to Table of contents

Primeur weekly 2017-01-30

Exascale supercomputing

Co-design centres to help make next-generation exascale computing a reality ...

Quantum computing

Supercool electrons ...

D-Wave announces D-Wave 2000Q quantum computer and first system order ...

Temporal Defense Systems purchases the first D-Wave 2000Q quantum computer ...

Fast track control accelerates switching of quantum bits ...

Focus on Europe

Bright Computing teams up with SGI to co-sponsor UK HPC & Big Data event ...

When life sciences become data sciences ...

PRACE Spring School 2017 - HPC for Life Sciences, registration is open ...

ITER and BSC tighten their collaboration to simulate the process of fusion power generation ...

Netherlands eScience Center to issue annual report ...

Middleware

BSC releases PyCOMPSs version 2.0 as a PIP installable package ...

Hardware

RSC gets the highest Elite status in the Intel Solutions for Lustre Reseller Programme ...

Finding a needle in the ocean ...

GIGABYTE selects Cavium QLogic 10/25GbE FastLinQ technology to power its next generation servers ...

Setting up light paths using the SURFnet Network Dashboard ...

Minerva will calculate gravitational waves faster than the Albert Einstein Institute's previous supercomputer ...

Applications

Big Brother will have some difficulty 'watching you' in future ...

Engineers eat away at Ms. Pac-Man score with artificial player ...

Mummy visualization impresses in computer journal ...

Berkeley launches RISELab, enabling computers to make intelligent real-time decisions ...

Model sheds light on inhibitory neurons' computational role ...

Using Big Data to understand immune system responses ...

Artificial intelligence uncovers new insight into biophysics of cancer ...

PPPL scientist uncovers physics behind plasma-etching process ...

Computer-aided drug design ...

IBM expands choices for PowerAI developers with TensorFlow ...

Hussein Aluie awarded hours on supercomputer at Argonne ...

CWI develops algorithms that shorten response time of ambulance ...

A rising peptide: Supercomputing helps scientists come closer to tailoring drug molecules ...

The Cloud

Oracle expands Startup Accelerator Programme to further promote global Cloud innovation ...

Technical computing hub UberCloud receives funding from Earlybird ...

Engineers eat away at Ms. Pac-Man score with artificial player


A screen capture of the Ms. Pac-Man game showing control vector sign conventions used in the study. Provided by Rob Kurcoba.
23 Jan 2017 Ithaca - Using a novel approach for computing real-time game strategy, engineers have developed an artificial Ms. Pac-Man player that chomps the existing high score for computerized play.

In the popular arcade game, Ms. Pac-Man must evade ghost enemies while she collects items and navigates an obstacle-populated maze. The game is somewhat of a favourite among engineers and computer scientists who compete to see who can program the best artificial player.

The record score at the annual Ms. Pac-Man Screen Capture Competition stands at 36,280, but a trio of researchers led by Silvia Ferrari, professor of mechanical and aerospace engineering at Cornell, has produced a laboratory score of 43,720.

The score was achieved using a decision-tree approach in which the optimal moves for the artificial player are derived from a maze of geometry and dynamic equations that predict the movements of the ghosts with 94.6-percent accuracy. As the game progresses, the decision tree is updated in real-time. The strategy is detailed in the study "A Model-Based Approach to Optimizing Ms. Pac-Man Game Strategies in Real Time", to be published by the journalIEEE Transactions on Computational Intelligence and AI in Games.

"The novelty of our method is in how the decision tree is generated, combining both geometric elements of the maze with information-gathering objectives", stated Silvia Ferrari, who noted that the information in this case is the fruit Ms. Pac-Man collects for bonus points. Her team is the first to mathematically model the game's components, whereas previous artificial players were developed with model-free methods.

Engineers take an interest in artificial players because they provide a benchmark challenge for developing new computational methods that can be applied to practical needs such as surveillance, search-and-rescue and mobile robotics.

"Engineering problems are so complicated, they're very difficult to translate across applications. But games are very understandable and can be used to compare different algorithms unambiguously because every algorithm can be applied to the same game", Silvia Ferrari stated.

What began as such an exercise became a spectacle in 1996 when Deep Blue, a chess-playing computer developed by IBM, defeated world champion Garry Kasparov in their first match. However, it took Deep Blue 11 more matches to defeat Garry Kasparov again.

Silvia Ferrari's Ms. Pac-Man player faces its own challenges against human players. The study found that the artificial player was not able to average better scores or produce higher scores against humans who routinely played the game.

"It's very interesting which problems are easier for humans and which are easier for computers", stated Silvia Ferrari. "It's not completely understood right now what elements of a problem allow humans to outperform computers and it is a question we are investigating with neuroscientists through collaborative projects supported by the Office of Naval Research and the National Science Foundation.

"In the case of Ms. Pac-Man, our mathematical model is very accurate, but the player remains imperfect because of an element of uncertainty in the decisions made by the ghosts."

However, Silvia Ferrari's model did produce better scores than beginners and players with intermediate skills. The artificial player also demonstrated that it was more skilled than advanced players in the upper levels of the game where speed and spatial complexity become more challenging.

While the Ms. Pac-Man Screen Capture Competition is now on indefinite hiatus, Silvia Ferrari said she may still revisit the project and improve the artificial player by adding a component that would allow it to autonomously learn from its mistakes as it plays more games.

The study is co-authored by Greg Foderaro, a staff engineer at Applied Research Associates, and Ashleigh Swingler, an engineering doctoral student at Duke University.

Source: Cornell University

Back to Table of contents

Primeur weekly 2017-01-30

Exascale supercomputing

Co-design centres to help make next-generation exascale computing a reality ...

Quantum computing

Supercool electrons ...

D-Wave announces D-Wave 2000Q quantum computer and first system order ...

Temporal Defense Systems purchases the first D-Wave 2000Q quantum computer ...

Fast track control accelerates switching of quantum bits ...

Focus on Europe

Bright Computing teams up with SGI to co-sponsor UK HPC & Big Data event ...

When life sciences become data sciences ...

PRACE Spring School 2017 - HPC for Life Sciences, registration is open ...

ITER and BSC tighten their collaboration to simulate the process of fusion power generation ...

Netherlands eScience Center to issue annual report ...

Middleware

BSC releases PyCOMPSs version 2.0 as a PIP installable package ...

Hardware

RSC gets the highest Elite status in the Intel Solutions for Lustre Reseller Programme ...

Finding a needle in the ocean ...

GIGABYTE selects Cavium QLogic 10/25GbE FastLinQ technology to power its next generation servers ...

Setting up light paths using the SURFnet Network Dashboard ...

Minerva will calculate gravitational waves faster than the Albert Einstein Institute's previous supercomputer ...

Applications

Big Brother will have some difficulty 'watching you' in future ...

Engineers eat away at Ms. Pac-Man score with artificial player ...

Mummy visualization impresses in computer journal ...

Berkeley launches RISELab, enabling computers to make intelligent real-time decisions ...

Model sheds light on inhibitory neurons' computational role ...

Using Big Data to understand immune system responses ...

Artificial intelligence uncovers new insight into biophysics of cancer ...

PPPL scientist uncovers physics behind plasma-etching process ...

Computer-aided drug design ...

IBM expands choices for PowerAI developers with TensorFlow ...

Hussein Aluie awarded hours on supercomputer at Argonne ...

CWI develops algorithms that shorten response time of ambulance ...

A rising peptide: Supercomputing helps scientists come closer to tailoring drug molecules ...

The Cloud

Oracle expands Startup Accelerator Programme to further promote global Cloud innovation ...

Technical computing hub UberCloud receives funding from Earlybird ...