Evaluating Influence Diagrams using LIMIDs
This work addresses efficiency issues in decision analysis for researchers and practitioners, though it appears incremental as it builds on existing influence diagram frameworks.
The paper tackles the problem of solving decision problems modeled as influence diagrams by converting them into Limited Memory Influence Diagrams (LIMIDs), which explicitly represent only necessary information for optimal policy computation, resulting in significant memory and computational time savings compared to traditional methods.
We present a new approach to the solution of decision problems formulated as influence diagrams. The approach converts the influence diagram into a simpler structure, the LImited Memory Influence Diagram (LIMID), where only the requisite information for the computation of optimal policies is depicted. Because the requisite information is explicitly represented in the diagram, the evaluation procedure can take advantage of it. In this paper we show how to convert an influence diagram to a LIMID and describe the procedure for finding an optimal strategy. Our approach can yield significant savings of memory and computational time when compared to traditional methods.