A Complete Criterion for Value of Information in Soluble Influence Diagrams

TL;DR

This paper introduces a comprehensive graphical criterion for evaluating the value of information in influence diagrams with multiple decisions, advancing analysis of AI safety and fairness.

Contribution

It presents the first complete criterion for VoI in multi-decision influence diagrams and introduces new techniques like ID homomorphisms and Tree of Systems.

Findings

Established a complete graphical criterion for VoI in multi-decision influence diagrams.

Developed ID homomorphisms as structure-preserving transformations.

Introduced Tree of Systems to analyze information and control flow.

Abstract

Influence 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 important techniques for proving properties of multi-decision influence diagrams: ID homomorphisms are structure-preserving transformations of influence diagrams, while a Tree of Systems is collection of paths that captures how information and control can flow in an influence diagram.