A Complete Criterion for Value of Information in Soluble Influence Diagrams
Keywords:Reasoning Under Uncertainty (RU)
AbstractInfluence diagrams have recently been used to analyse the safety and fairness properties of AI systems. A key building block for this analysis is a graphical criterion for value of information (VoI). This paper establishes the first complete graphical criterion for VoI in influence diagrams with multiple decisions. Along the way, we establish two techniques for proving properties of multi-decision influence diagrams: ID homomorphisms are structure-preserving transformations of influence diagrams, while a Tree of Systems is a collection of paths that captures how information and control can flow in an influence diagram.
How to Cite
Merwijk, C. van, Carey, R., & Everitt, T. (2022). A Complete Criterion for Value of Information in Soluble Influence Diagrams. Proceedings of the AAAI Conference on Artificial Intelligence, 36(9), 10034-10041. https://doi.org/10.1609/aaai.v36i9.21242
AAAI Technical Track on Reasoning under Uncertainty