mlsanityData to 7 Oct 2026

A Complete Criterion for Value of Information in Soluble Influence Diagrams

arXiv 2202.11629 ↗First posted 23 Feb 2022cs.AI stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 16 of its 45 references that are in the map. First posted on arXiv 23 Feb 2022.

Builds on

16 of 45 references.

References · 16

  1. 2017Counterfactual Fairnesscited by 802
  2. 2016Cooperative Inverse Reinforcement Learningcited by 298
  3. 2019Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspectivecited by 107
  4. 2013Causal Networks: Semantics and Expressivenesscited by 67
  5. 2021Agent Incentives: A Causal Perspectivecited by 51
  6. 2021User Tampering in Reinforcement Learning Recommender Systemscited by 23
  7. 2017Should Robots be Obedient?cited by 20
  8. 2013Bayes-Ball: The Rational Pastime (for Determining Irrelevance and Requisite Information in Belief Networks and Influence Diagrams)cited by 18
  9. 2021How RL Agents Behave When Their Actions Are Modifiedcited by 10
  10. 2022Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairnesscited by 10
  11. 2021Equilibrium Refinements for Multi-Agent Influence Diagrams: Theory and Practicecited by 9
  12. 2019Modeling AGI Safety Frameworks with Causal Influence Diagramscited by 8
4 more
  1. 2020AGI Agent Safety by Iteratively Improving the Utility Functioncited by 8
  2. 2019Asymptotically Unambitious Artificial General Intelligencecited by 7
  3. 2013Evaluating Influence Diagrams using LIMIDscited by 2
  4. 2013Welldefined Decision Scenarioscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 0; 2026: 1.

5 papers.

  1. 2024Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systemscited by 94
  2. 2024The Reasons that Agents Act: Intention and Instrumental Goalscited by 23
  3. 2023On Imperfect Recall in Multi-Agent Influence Diagramscited by 4
  4. 2023Unfair Utilities and First Steps Towards Improving Themcited by 0
  5. 2026The Design and Composition of Structural Causal Decision Processescited by 0