Information/Relevance Influence Diagrams
This work addresses a specific need for users of influence diagrams who want to represent decision constraints more directly, but it is incremental as it extends an existing representation.
The paper tackles the problem of representing constraints on decisions in influence diagrams (IDs) by introducing information/relevance influence diagrams (IRIDs), which allow direct representation of constraints through relevance arrows into decision nodes, and they solve IRIDs using a combination of stochastic dynamic programming and Gibbs sampling, especially when exact methods fail.
In this paper we extend the influence diagram (ID) representation for decisions under uncertainty. In the standard ID, arrows into a decision node are only informational; they do not represent constraints on what the decision maker can do. We can represent such constraints only indirectly, using arrows to the children of the decision and sometimes adding more variables to the influence diagram, thus making the ID more complicated. Users of influence diagrams often want to represent constraints by arrows into decision nodes. We represent constraints on decisions by allowing relevance arrows into decision nodes. We call the resulting representation information/relevance influence diagrams (IRIDs). Information/relevance influence diagrams allow for direct representation and specification of constrained decisions. We use a combination of stochastic dynamic programming and Gibbs sampling to solve IRIDs. This method is especially useful when exact methods for solving IDs fail.