On probability-raising causality in Markov decision processes

2022/01/21 by Baier, Christel, Funke, Florian, Piribauer, Jakob +1 · 2 citations
#FOS: Computer and information sciences #Logic in Computer Science (cs.LO)

paper · doi:10.48550/arxiv.2201.08768

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.

Cited by

• Efficient Discovery of Actual Causality in Stochastic Systems
• Probability-Raising Causality for Uncertain Parametric Markov Decision Processes with PAC Guarantees

Related

• Probabilistic causes in Markov chains
• Probability-Raising Causality for Uncertain Parametric Markov Decision Processes with PAC Guarantees
• Causal Explanations for Sequential Decision Making Under Uncertainty
• Property-driven Causal Abstractions for Markov Decision Processes
• Causal Markov Decision Processes: Learning Good Interventions Efficiently