Remembering to Be Fair: Non-Markovian Fairness in Sequential Decision Making

arXiv:2312.04772v3 Announce Type: replace-cross
Abstract: Fair decision making has largely been studied with respect to a single decision. In this paper we investigate the notion of fairness in the context of sequential decision making where multiple stakeholders can be affected by the outcomes of decisions. We observe that fairness often depends on the history of the sequential decision-making process, and in this sense that it is inherently non-Markovian. We further observe that fairness often needs to be assessed at time …

abstract arxiv context cs.ai cs.cy cs.lg decision decision making decisions fair fairness making multiple notion observe paper stakeholders type