Graphical Languages for Specification of Decision Problems
A Bayesian network serves as a model for a part of the world, and the relations in the model reflect causal impact between events. The reason for building these computer models is to use them when taking decisions. In other words, the probabilities provided by the network are used to support some kind of decision making. In principle, there are two kinds of decisions, namely test decisions and action decisions.
KeywordsDecision Tree Bayesian Network Decision Problem Expected Utility Markov Decision Process
Unable to display preview. Download preview PDF.