Assessing the Time Efficiency of Ethical Algorithms
(2022) AIC 2022 In CEUR Workshop Proceedings- Abstract
- Artificial moral agents must not only be able to make competent ethical decisions, but they must do so effectively. This paper explores how ethical theory and algorithmic design impact computational efficiency by assessing the time cost of ethical algorithms. We create a model of an ethical environmentand conduct experiments on three different ethical algorithms in order to compare computational benefits and disadvantages of deontology and consequentialism respectively. The experimental results highlight the close relationship between ethical theory, algorithmic design, and resource costs, and our work provides an important starting-point for the further examination of these relations. Lastly, we introduce the concept of moral tractability... (More)
- Artificial moral agents must not only be able to make competent ethical decisions, but they must do so effectively. This paper explores how ethical theory and algorithmic design impact computational efficiency by assessing the time cost of ethical algorithms. We create a model of an ethical environmentand conduct experiments on three different ethical algorithms in order to compare computational benefits and disadvantages of deontology and consequentialism respectively. The experimental results highlight the close relationship between ethical theory, algorithmic design, and resource costs, and our work provides an important starting-point for the further examination of these relations. Lastly, we introduce the concept of moral tractability as a venue for future work. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/234a0858-f7de-4149-87fe-f5d0b04ce07a
- author
- Stenseke, Jakob LU and Balkenius, Christian LU
- organization
- publishing date
- 2022-06-15
- type
- Contribution to journal
- publication status
- epub
- subject
- keywords
- Machine ethics, Computational complexity, Consequentialism, Deontology, Machine ethics, Computational complexity, Consequentialism, Deontology
- in
- CEUR Workshop Proceedings
- pages
- 9 pages
- publisher
- CEUR-WS
- conference name
- AIC 2022
- conference location
- Örebro, Sweden
- conference dates
- 2022-07-15 - 2022-07-17
- ISSN
- 1613-0073
- project
- Lund University AI Research
- How to build nice robots: ethics from theory to machine implementations
- Ethics for autonomous systems/AI
- language
- English
- LU publication?
- yes
- id
- 234a0858-f7de-4149-87fe-f5d0b04ce07a
- alternative location
- https://aic20.aass.oru.se/aic-pdfs/AIC-2022-camera-ready-short-paper-16.pdf
- date added to LUP
- 2022-08-01 11:42:29
- date last changed
- 2023-01-10 16:20:35
@article{234a0858-f7de-4149-87fe-f5d0b04ce07a, abstract = {{Artificial moral agents must not only be able to make competent ethical decisions, but they must do so effectively. This paper explores how ethical theory and algorithmic design impact computational efficiency by assessing the time cost of ethical algorithms. We create a model of an ethical environmentand conduct experiments on three different ethical algorithms in order to compare computational benefits and disadvantages of deontology and consequentialism respectively. The experimental results highlight the close relationship between ethical theory, algorithmic design, and resource costs, and our work provides an important starting-point for the further examination of these relations. Lastly, we introduce the concept of moral tractability as a venue for future work.}}, author = {{Stenseke, Jakob and Balkenius, Christian}}, issn = {{1613-0073}}, keywords = {{Machine ethics; Computational complexity; Consequentialism; Deontology; Machine ethics; Computational complexity; Consequentialism; Deontology}}, language = {{eng}}, month = {{06}}, publisher = {{CEUR-WS}}, series = {{CEUR Workshop Proceedings}}, title = {{Assessing the Time Efficiency of Ethical Algorithms}}, url = {{https://aic20.aass.oru.se/aic-pdfs/AIC-2022-camera-ready-short-paper-16.pdf}}, year = {{2022}}, }