The Simulation Of Coadaptive Decision-making
Andreas Glöckner · 2005
Decision-making in distributed computing systems is complicated by the introduction of communication delays. This results in uncertainty about both the global system state and the current actions of the system. One of the methods of addressin this difficulty making. By constructing the decision-making process as a set of autonomous agents that can individually learn from feedback, the set of agents adapt together, or coadapt, to form a good, though not necessarily op timal, global decision process. In this paper, a model of coadaptive decisionmaking in a small distributed computing system is described and justified. Some of the simulation results from this ongoing investigation are presented with ap propriate conclusions.