Publikationsansicht

Unobtrusive workstation farming without inconveniencing owners: Learning Backgammon with a genetic algorithm (1999)

Abstract
Most efforts at low-cost parallel computing assume a monopoly on the hardware being used. That all-or-nothing attitude ignores many machines dedicated to other activities, but which sit idle for 16 hours a day. However, naïve attempts to utilize idle machines can interfere with their primary purpose. This paper describes the successful effort to unobtrusively farm idle machines, for an artificial intelligence system using a genetic algorithm to learn the game Backgammon. It maintains owners ’ full access to their machines, without causing any detectable interference. 1

Details der Publikation
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.63.6609
Quelle http://paul.darwen.org/pubs/iwcc99.pdf
Herausgeber IEEE Computer Society Press
Mitarbeiter CiteSeerX
Archiv CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Typ text
Sprache Englisch
Verknüpfungen 10.1.1.102.9485, 10.1.1.20.3760, 10.1.1.41.3469, 10.1.1.57.7053, 10.1.1.78.3054, 10.1.1.38.6434, 10.1.1.46.6818, 10.1.1.43.8155, 10.1.1.29.388, 10.1.1.47.5934, 10.1.1.98.2173, 10.1.1.26.9620, 10.1.1.25.9445, 10.1.1.20.9071, 10.1.1.29.3317