Unobtrusive workstation farming without inconveniencing owners: learning Backgammon with a genetic algorithm

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 naive 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