Have a break from making decisions, have a MARS: The Multi-valued Action Reasoning System

TL;DR

MARS is an automated system for ethical decision-making in AI that identifies morally preferred actions based on various ethical theories and paradigms, aiding in modeling dilemmas and normative reasoning.

Contribution

Introduces MARS, a novel multi-valued action reasoning system for ethical decision-making in AI, capable of modeling diverse moral paradigms and dilemmas.

Findings

MARS effectively models different ethical theories.

It can identify ethically preferred actions in complex scenarios.

The system offers a flexible framework for normative decision analysis.

Abstract

The Multi-valued Action Reasoning System (MARS) is an automated value-based ethical decision-making model for artificial agents (AI). Given a set of available actions and an underlying moral paradigm, by employing MARS one can identify the ethically preferred action. It can be used to implement and model different ethical theories, different moral paradigms, as well as combinations of such, in the context of automated practical reasoning and normative decision analysis. It can also be used to model moral dilemmas and discover the moral paradigms that result in the desired outcomes therein. In this paper, we give a condensed description of MARS, explain its uses, and comparatively place it in the existing literature.