Uncertain Machine Ethics Planning

TL;DR

This paper formalizes the challenge of making ethical decisions under uncertainty in machine ethics by proposing a Multi-Moral Markov Decision Process framework and a heuristic algorithm, validated through a case study involving insulin theft.

Contribution

It introduces a formal multi-moral decision-making model and a heuristic solution method for ethical planning under uncertainty in machine ethics.

Findings

The proposed model captures conflicting moral theories.

The heuristic algorithm effectively balances moral considerations.

Case study demonstrates practical applicability.

Abstract

Machine Ethics decisions should consider the implications of uncertainty over decisions. Decisions should be made over sequences of actions to reach preferable outcomes long term. The evaluation of outcomes, however, may invoke one or more moral theories, which might have conflicting judgements. Each theory will require differing representations of the ethical situation. For example, Utilitarianism measures numerical values, Deontology analyses duties, and Virtue Ethics emphasises moral character. While balancing potentially conflicting moral considerations, decisions may need to be made, for example, to achieve morally neutral goals with minimal costs. In this paper, we formalise the problem as a Multi-Moral Markov Decision Process and a Multi-Moral Stochastic Shortest Path Problem. We develop a heuristic algorithm based on Multi-Objective AO*, utilising Sven-Ove Hansson's Hypothetical Retrospection procedure for ethical reasoning under uncertainty. Our approach is validated by a case study from Machine Ethics literature: the problem of whether to steal insulin for someone who needs it.