Solving Hybrid Influence Diagrams with Deterministic Variables
نویسندگان
چکیده
We describe a framework and an algorithm for solving hybrid influence diagrams with discrete, continuous, and deterministic chance variables, and discrete and continuous decision variables. A continuous chance variable in an influence diagram is said to be deterministic if its conditional distributions have zero variances. The solution algorithm is an extension of Shenoy’s fusion algorithm for discrete influence diagrams. We describe an extended Shenoy-Shafer architecture for propagation of discrete, continuous, and utility potentials in hybrid influence diagrams that include deterministic chance variables. The algorithm and framework are illustrated by solving two small examples.
منابع مشابه
A Framework for Solving Hybrid Influence Diagrams Containing Deterministic Conditional Distributions
W describe a framework and an algorithm for approximately solving a class of hybrid influence diagrams (IDs) containing discrete and continuous chance variables, discrete and continuous decision variables, and deterministic conditional distributions for chance variables. A conditional distribution for a chance variable is said to be deterministic if its variances, for each state of its parents,...
متن کاملArc reversals in hybrid Bayesian networks with deterministic variables
This article discusses arc reversals in hybrid Bayesian networks with deterministic variables. Hybrid Bayesian networks contain a mix of discrete and continuous chance variables. In a Bayesian network representation, a continuous chance variable is said to be deterministic if its conditional distributions have zero variances. Arc reversals are used in making inferences in hybrid Bayesian networ...
متن کاملQualitative Reasoning About Constraint Activity Using Monotonic Influence Diagrams
Monotonic influence diagrams (MID) are proposed for representing and manipulating qualitative and mathematical relationships between variables and constraints in order to design from physical principles. The theory of MID’s is based on a graph-theoretic representation of an optimization problem which can be topologically transformed as a means of solving the problem and exploring variable-objec...
متن کاملMultistage Monte Carlo Method for Solving Influence Diagrams Using Local Computation
T main goal of this paper is to describe a new multistage Monte Carlo (MMC) simulation method for solving influence diagrams using local computation. Global methods have been proposed by others that sample from the joint probability distribution of all the variables in the influence diagram. However, for influence diagrams having many variables, the state space of all variables grows exponentia...
متن کاملIssues in Bayes Nets and Influence Diagrams: With Applications in Accounting and Auditing
Recently substantial research in artificial intelligence (AI) has focused on Bayes nets and the closely related influence diagrams. However, there has been little work in the accounting and auditing communi ties in this area of AI research. Bayes nets and influence diagrams have some advantages over deterministic AI approaches. These approaches employ probabilities to model decision making. Pr...
متن کامل