On probability-raising causality in Markov decision processes

TL;DR

This paper introduces a causality concept in Markov decision processes based on probability-raising, providing algorithms for cause-effect analysis, quality measurement, and complexity assessment.

Contribution

It presents a novel causality framework for MDPs using probability-raising and develops algorithms for cause detection and quality evaluation.

Findings

Algorithms for cause-effect relationship checking

Methods for measuring cause quality (recall, coverage, f-score)

Complexity analysis of finding optimal causes

Abstract

The purpose of this paper is to introduce a notion of causality in Markov decision processes based on the probability-raising principle and to analyze its algorithmic properties. The latter includes algorithms for checking cause-effect relationships and the existence of probability-raising causes for given effect scenarios. Inspired by concepts of statistical analysis, we study quality measures (recall, coverage ratio and f-score) for causes and develop algorithms for their computation. Finally, the computational complexity for finding optimal causes with respect to these measures is analyzed.