- Title
- Human-aligned artificial intelligence is a multiobjective problem
- Creator
- Vamplew, Peter; Dazeley, Richard; Foale, Cameron; Firmin, Sally; Mummery, Jane
- Date
- 2018
- Type
- Text; Journal article
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/164225
- Identifier
- vital:13031
- Identifier
-
https://doi.org/10.1007/s10676-017-9440-6
- Identifier
- ISBN:1388-1957
- Abstract
- As the capabilities of artificial intelligence (AI) 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 (MEU) 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. © 2017, Springer Science+Business Media B.V.
- Publisher
- Springer Netherlands
- Relation
- Ethics and Information Technology Vol. 20, no. 1 (2018), p. 27-40
- Rights
- Copyright © 2017, Springer Science+Business Media B.V.
- Rights
- This metadata is freely available under a CCO license
- Subject
- 1604 Human Geography; 2201 Applied Ethics; 2203 Philosophy; Aligned artificial intelligence; Ethics; Maximum Expected Utility; Reward engineering; Value alignment
- Full Text
- Reviewed
- Hits: 6696
- Visitors: 7679
- Downloads: 1320
Thumbnail | File | Description | Size | Format | |||
---|---|---|---|---|---|---|---|
View Details Download | SOURCE1 | Submitted version | 397 KB | Adobe Acrobat PDF | View Details Download |