Artificial virtuous agents in a multi‐agent tragedy of the commons
(2024) In AI & Society: Knowledge, Culture and Communication 39(3). p.855-872- 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... (More)
- 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. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/4bb94731-e856-4426-a2df-dd817cf5e0e8
- author
- Stenseke, Jakob LU
- organization
- publishing date
- 2024
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Machine ethics, Artificial moral agents, virtue ethics, AI ethics, ethics of autonomous systems, artificial morality, Machine ethics, Artificial morality, Artificial moral agents, Virtue ethics, AI ethics, Ethics of autonomous systems
- in
- AI & Society: Knowledge, Culture and Communication
- volume
- 39
- issue
- 3
- pages
- 18 pages
- publisher
- Springer
- external identifiers
-
- scopus:85139424823
- ISSN
- 1435-5655
- DOI
- 10.1007/s00146-022-01569-x
- project
- How to build nice robots: ethics from theory to machine implementations
- Ethics for autonomous systems/AI
- Instrumental and normative expectations in a social robot
- language
- English
- LU publication?
- yes
- id
- 4bb94731-e856-4426-a2df-dd817cf5e0e8
- date added to LUP
- 2022-10-06 10:44:23
- date last changed
- 2024-07-23 11:24:13
@article{4bb94731-e856-4426-a2df-dd817cf5e0e8, 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.}}, author = {{Stenseke, Jakob}}, issn = {{1435-5655}}, keywords = {{Machine ethics; Artificial moral agents; virtue ethics; AI ethics; ethics of autonomous systems; artificial morality; Machine ethics; Artificial morality; Artificial moral agents; Virtue ethics; AI ethics; Ethics of autonomous systems}}, language = {{eng}}, number = {{3}}, pages = {{855--872}}, publisher = {{Springer}}, series = {{AI & Society: Knowledge, Culture and Communication}}, title = {{Artificial virtuous agents in a multi‐agent tragedy of the commons}}, url = {{https://lup.lub.lu.se/search/files/125083987/AVA20510.pdf}}, doi = {{10.1007/s00146-022-01569-x}}, volume = {{39}}, year = {{2024}}, }