Quasi-Dilemmas for Artificial Moral Agents

TL;DR

This paper introduces moral quasi-dilemmas (MQDs), situations where artificial moral agents must explore options to find morally acceptable actions, highlighting their importance for designing and evaluating AMA architectures.

Contribution

It defines MQDs, argues for their relevance in AMA development, and suggests using MQDs to assess AMA architectures' moral reasoning capabilities.

Findings

MQDs are similar to moral dilemmas but involve uncertainty in moral resolution.

AMAs should explore plan space rather than accept dilemmas as unavoidable.

MQDs can serve as benchmarks for evaluating AMA architectures.

Abstract

In this paper we describe moral quasi-dilemmas (MQDs): situations similar to moral dilemmas, but in which an agent is unsure whether exploring the plan space or the world may reveal a course of action that satisfies all moral requirements. We argue that artificial moral agents (AMAs) should be built to handle MQDs (in particular, by exploring the plan space rather than immediately accepting the inevitability of the moral dilemma), and that MQDs may be useful for evaluating AMA architectures.