A Generalized Maximum Entropy Principle

We describe a generalized maximum entropy principle for dealing with decision problems involving uncertainty but with some prior knowledge about the probability space corresponding to nature. This knowledge is expressed through known bounds on event probabilities and moments, which can be incorporated into a nonlinear programming problem. The solution provides a maximum entropy distribution that is then used in treating the decision problem as one involving risk. We describe an example application that involves the selection of oil spill recovery systems for inland harbor regions.