A Method for Using Belief Networks as Influence Diagrams

Abstract

This paper demonstrates a method for using belief-network algorithms to solve influence diagram problems. In particular, both exact and approximation belief-network algorithms may be applied to solve influence-diagram problems. More generally, knowing the relationship between belief-network and influence-diagram problems may be useful in the design and development of more efficient influence diagram algorithms.

Appears in Proceedings of the Fourth Conference on Uncertainty in Artificial Intelligence (UAI1988)

References in corpus (1)

• Updating Probabilities in Multiply-Connected Belief Networks

Cited by in corpus (10)

• Optimal control as a graphical model inference problem
• Solving Factored MDPs with Hybrid State and Action Variables
• Planning with Noisy Probabilistic Relational Rules
• The Complexity of Approximately Solving Influence Diagrams
• Multi-objective Influence Diagrams
• Iterative Amortized Policy Optimization
• A Sensitivity Analysis of Pathfinder
• Knowledge-Based Decision Model Construction for Hierarchical Diagnosis: A Preliminary Report
• Decision Making Using Probabilistic Inference Methods
• BaRT: A Bayesian Reasoning Tool for Knowledge Based Systems