Foundations of probability-raising causality in Markov decision processes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Baier, Christel, Piribauer, Jakob, Ziemek, Robin
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914901361950720
author Baier, Christel
Piribauer, Jakob
Ziemek, Robin
author_facet Baier, Christel
Piribauer, Jakob
Ziemek, Robin
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2209_02973
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Foundations of probability-raising causality in Markov decision processes
Baier, Christel
Piribauer, Jakob
Ziemek, Robin
Logic in Computer Science
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.
title Foundations of probability-raising causality in Markov decision processes
topic Logic in Computer Science
url https://arxiv.org/abs/2209.02973