My Shopping Cart

[ 0 ]

View Cart | Checkout

Game Developer Research
bullet Research Reports

bullet Contractor Listings

GDC Vault
bullet Individual Subscription

GDC Audio Recordings
bullet App Developers Conference 2013
bullet GDC Next 2013
bullet GDC Europe 2013
bullet GDC 2013
bullet GDC Online 2012
bullet GDC Europe 2012
bullet GDC 2012
bullet GDC 2011
bullet GDC 10
bullet GDC 09
bullet GDC Austin 08
bullet GDC Mobile 08
bullet GDC 08
bullet GDC Austin 07
bullet GDC Mobile 07
bullet GDC 07
bullet GDC 06
bullet GDC 05
bullet GDC 04
bullet GDC 03
bullet GDC 01
bullet GDC 2000 & Before

Newest Item(s)

Why Now Is the Best Time Ever to Be a Game Developer

Ingress: Design Principles Behind Google's Massively Multiplayer Geo Game

Playing with 'Game'

Gathering Your Party with Project Eternity (GDC Next 10)

D4: Dawn of the Dreaming Director's Drama (GDC Next 10)

Using Plot Devices to Create Gameplay in Storyteller (GDC Next 10)

How I Learned to Stop Worrying and Love Making CounterSpy (GDC Next 10)

Luck and Skill in Games

Minimalist Game Design for Mobile Devices

Broken Age: Rethinking a Classic Genre for the Modern Era (GDC Next 10)

Storefront > GDC Vault Store - Audio Recordings > More GDC > GDC 2005

View larger image


Machine Learning for Semi-Automated Gameplay Analysis
Price $5.95
Stock Unlimited
Weight 0 lb, 0 oz
SKU GDC-05-147
Machine Learning for Semi-Automated Gameplay Analysis,

Game Design, Lecture

Finnegan Southey
Research Associate, University of Alberta, Dpt of Computing Science

John Buchanan
University Research Liaison, Electronic Arts
Compelling gameplay requires constant testing and refinement during the development process, amounting to a considerable investment in time and energy. This talk presents an approach to gameplay analysis intended to support and augment the work of game designers, collecting and summarizing gameplay information from the game engine so designers can quickly evaluate the behaviour to make decisions. Using readily available machine learning technologies, a reusable tool has been constructed that can repeatedly choose scenarios to examine, run them through the game engine, and then construct concise and informative summaries of the engine's behaviour for designers. Based on the past scenarios, new scenarios are intelligently chosen to verify uncertain conclusions and refine the analysis. Game designers can examine the summaries produced by the analyzer, typically with a secondary visualization tool, providing the essential human judgement on what constitutes reasonable and entertaining behaviour. The inevitable role of the designer is why we use the term `semi-automated'. The analysis tool, SAGA-ML (Semi-Automated Gampeplay Analysis by Machine Learning), is based on machine learning research known as `active learning', and has been used to evaluate Electronic Arts' FIFA'99 soccer game, uncovering some interesting anomalies in gameplay. With only minor changes, the tool was interfaced to FIFA 2004, and plays an active, in-house role in the development and testing of FIFA 2005. While designed and developed in this context, the analysis tool is general purpose, requiring only a thin interface layer to be written to connect to different game engines. For the specific case of FIFA, a visualization tool, SoccerViz, has also been developed. SAGA-ML and SoccerViz were designed and developed by the University of Alberta GAMES group in cooperation with Electronic Arts.
Contributors/authors on this paper: John Buchanan, Electronic Arts, Robert Holte, Computing Science, University of Alberta, Finnegan Southey, Computing Science, University of Alberta, Gang Xiao, Computing Science, University of Alberta, Mark Trommelen, Alberta Ingenuity Centre for Machine Learning

Readily available methods from machine learning can be used to analyze gameplay to support designers during development. A demo of the general-purpose, reusable SAGA-ML tool shows the methodology applied to Electronic Arts' FIFA soccer game.

Please leave this field blank.

There are no related products to display.

Related Products...

Please leave this field blank.