This paper presents an architecture for exact evaluation of influence diagrams containing a mixture of continuous and discrete variables. The proposed architecture is the first architecture for efficient exact solution of linear-quadratic conditional Gaussian influence diagrams with an additively decomposing utility function. The solution method as presented in this paper is based on the idea of lazy evaluation. The computational aspects of the architecture are illustrated by example.
CITATION STYLE
Madsen, A. L., & Jensen, P. (2003). Mixed influence diagrams. In Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science) (Vol. 2711, pp. 208–219). Springer Verlag. https://doi.org/10.1007/978-3-540-45062-7_17
Mendeley helps you to discover research relevant for your work.