A Complete Criterion for Value of Information in Soluble Influence Diagrams

by   Chris van Merwijk, et al.

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.



page 1

page 2

page 3

page 4


Agent Incentives: A Causal Perspective

We present a framework for analysing agent incentives using causal influ...

Myopic Value of Information in Influence Diagrams

We present a method for calculation of myopic value of information in in...

Modeling AGI Safety Frameworks with Causal Influence Diagrams

Proposals for safe AGI systems are typically made at the level of framew...

Model-based Influence Diagrams for Machine Vision

We show an approach to automated control of machine vision systems based...

Understanding Agent Incentives using Causal Influence Diagrams, Part I: Single Action Settings

Agents are systems that optimize an objective function in an environment...

Unconstrained Influence Diagrams

We extend the language of influence diagrams to cope with decision scena...

Decreasing Diagrams for Confluence and Commutation

The decreasing diagrams technique is one of the strongest and most versa...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.