On probability-raising causality in Markov decision processes

01/21/2022
by   Christel Baier, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

06/01/2011

Nonapproximability Results for Partially Observable Markov Decision Processes

We show that for several variations of partially observable Markov decis...
04/28/2021

Probabilistic causes in Markov chains

The paper studies a probabilistic notion of causes in Markov chains that...
05/09/2012

The Temporal Logic of Causal Structures

Computational analysis of time-course data with an underlying causal str...
04/01/2022

Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes

Actual causality and a closely related concept of responsibility attribu...
01/25/2016

Conditional distribution variability measures for causality detection

In this paper we derive variability measures for the conditional probabi...
10/15/2018

Machine Self-Confidence in Autonomous Systems via Meta-Analysis of Decision Processes

Algorithmic assurances from advanced autonomous systems assist human use...
10/15/2018

Factorized Machine Self-Confidence for Decision-Making Agents

Algorithmic assurances from advanced autonomous systems assist human use...
This week in AI

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