FOUNDATIONS OF PROBABILITY-RAISING CAUSALITY IN MARKOV DECISION PROCESSES

Christel Baier, Jakob Piribauer, Robin Ziemek

Research output: Contribution to journalArticlepeer-review

Abstract

This work introduces a novel cause-effect relation in Markov decision processes using the probability-raising principle. Initially, sets of states as causes and effects are considered, which is subsequently extended to regular path properties as effects and then as causes. The paper lays the mathematical foundations and analyzes the algorithmic properties of these cause-effect relations. This includes algorithms for checking cause conditions given an effect and deciding the existence of probability-raising causes. As the definition allows for sub-optimal coverage properties, quality measures for causes inspired by concepts of statistical analysis are studied. These include recall, coverage ratio and f-score. The computational complexity for finding optimal causes with respect to these measures is analyzed.

Original languageEnglish
Article number66
JournalLogical Methods in Computer Science
Volume20
Issue number1
DOIs
StatePublished - 2024
Externally publishedYes

Keywords

  • binary classifier
  • Markov decision process
  • probabilistic causality
  • probability-raising

Fingerprint

Dive into the research topics of 'FOUNDATIONS OF PROBABILITY-RAISING CAUSALITY IN MARKOV DECISION PROCESSES'. Together they form a unique fingerprint.

Cite this