Ethics and Information Technology 20 (1):27-40 (2018)

As the capabilities of artificial intelligence systems improve, it becomes important to constrain their actions to ensure their behaviour remains beneficial to humanity. A variety of ethical, legal and safety-based frameworks have been proposed as a basis for designing these constraints. Despite their variations, these frameworks share the common characteristic that decision-making must consider multiple potentially conflicting factors. We demonstrate that these alignment frameworks can be represented as utility functions, but that the widely used Maximum Expected Utility paradigm provides insufficient support for such multiobjective decision-making. We show that a Multiobjective Maximum Expected Utility paradigm based on the combination of vector utilities and non-linear action–selection can overcome many of the issues which limit MEU’s effectiveness in implementing aligned AI. We examine existing approaches to multiobjective AI, and identify how these can contribute to the development of human-aligned intelligent agents.
Keywords No keywords specified (fix it)
Categories (categorize this paper)
DOI 10.1007/s10676-017-9440-6
Edit this record
Mark as duplicate
Export citation
Find it on Scholar
Request removal from index
Revision history

Download options

PhilArchive copy

Upload a copy of this paper     Check publisher's policy     Papers currently archived: 65,636
External links

Setup an account with your affiliations in order to access resources via your University's proxy server
Configure custom proxy (use this if your affiliation does not provide a proxy)
Through your library

References found in this work BETA

Superintelligence: Paths, Dangers, Strategies.Nick Bostrom (ed.) - 2014 - Oxford University Press.
The Right and the Good.Some Problems in Ethics.W. D. Ross & H. W. B. Joseph - 1933 - Journal of Philosophy 30 (19):517-527.

View all 15 references / Add more references

Citations of this work BETA

Artificial Moral Agents Within an Ethos of AI4SG.Bongani Andy Mabaso - 2020 - Philosophy and Technology 34 (1):7-21.

View all 7 citations / Add more citations

Similar books and articles

Socially Useful Artificial Intelligence.Richard Ennals - 1987 - AI and Society 1 (1):5-15.
Artificial Intelligence and Wittgenstein.Gerard Casey - 1988 - Philosophical Studies (Dublin) 32:156-175.
Ai: Its Nature and Future.Margaret A. Boden - 2016 - Oxford University Press UK.
Local Search for Multiobjective Function Optimization: Pareto Descent Method.Ken Harada, Jun Sakuma, Kokolo Ikeda, Isao Ono & Shigenobu Kobayashi - 2006 - Transactions of the Japanese Society for Artificial Intelligence 21:350-360.


Added to PP index

Total views
29 ( #383,136 of 2,462,232 )

Recent downloads (6 months)
5 ( #144,199 of 2,462,232 )

How can I increase my downloads?


My notes