Untitled Document
Not a member yet? Register for full benefits!

Username
Password
 Game Theoretic Machine Learning Methods Can Help Explain Long Periods of Conflict

This story is from the category Artificial Intelligence
Printer Friendly Version
Email to a Friend (currently Down)

 

 

Date posted: 24/05/2010

Researchers at the Santa Fe Institute have developed new machine learning methods to study conflict. Their work appears in PLOS Computational Biology on May 13.

Quantitative studies of behavior traditionally rely on game theory to investigate the logic of conflict. Game theory seeks to identify normative strategies that maximize payoffs for individuals in the face of uncertainty.

Although game theory has been very useful for determining which of a predefined set of strategies -- for example, "tit for tat" -- will be stable given certain assumptions, its has not proven to be very useful for determining what the natural strategy set is, or which strategies individuals are using out of equilibrium. Game theoretic models are also not practical for studying strategies when interactions involve multiple players interacting simultaneously. This is the case in many complex animal and human systems.

Santa Fe Institute Omidyar Postdoctoral Fellow Simon DeDeo and Institute faculty members Jessica Flack and David Krakauer developed the new method, which they call Inductive Game Theory, and applied it to a time series of fights gathered from detailed observations of an animal society model system.

"With these approaches, we can identify those strategies likely to generate periods of intense conflict," DeDeo says.

"Fights are not explained by 'rogue actors,' or single aggressive individuals, but by complex interactions among groups of three or higher, and the decision to fight is very much dependent on memory for what happened in previous conflicts," says Krakauer.

See the full Story via external site: www.sciencedaily.com



Most recent stories in this category (Artificial Intelligence):

03/03/2017: Application of Fuzzy Logic Teaches Drones to land on Moving Targets

02/03/2017: Poker-playing AI program first to beat pros at no-limit Texas hold 'em

05/02/2017: Google's driverless cars make progress

04/02/2017: Study Exposes Major Flaw in Turing Test

31/01/2017: Artificial intelligence uncovers new insight into biophysics of cancer

31/01/2017: Hungry penguins help keep smart car code safe

12/01/2017: First ever perched landing performed using machine learning algorithms

12/01/2017: AI takes on humans in marathon poker game