Artificial virtuous agents in a multiagent tragedy of the commons

TL;DR

This paper presents the first technical implementation of artificial virtuous agents in moral simulations, demonstrating their ability to learn cooperation and exhibit virtues in a tragedy of the commons scenario.

Contribution

It introduces a novel computational model of artificial virtuous agents based on virtue ethics, combining learning and eudaimonic reward in moral simulations.

Findings

AVAs learn to cooperate in the scenario

AVAs exhibit moral character and virtues

AVAs pursue eudaimonia through learning

Abstract

Although virtue ethics has repeatedly been proposed as a suitable framework for the development of artificial moral agents (AMAs), it has been proven difficult to approach from a computational perspective. In this work, we present the first technical implementation of artificial virtuous agents (AVAs) in moral simulations. First, we review previous conceptual and technical work in artificial virtue ethics and describe a functionalistic path to AVAs based on dispositional virtues, bottom-up learning, and top-down eudaimonic reward. We then provide the details of a technical implementation in a moral simulation based on a tragedy of the commons scenario. The experimental results show how the AVAs learn to tackle cooperation problems while exhibiting core features of their theoretical counterpart, including moral character, dispositional virtues, learning from experience, and the pursuit of eudaimonia. Ultimately, we argue that virtue ethics provides a compelling path toward morally excellent machines and that our work provides an important starting point for such endeavors.