Value Inference in Sociotechnical Systems
Blue Sky Ideas Track
Enrico Liscio (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Roger Lera-Leri (Institut d'Investigació en Intel·ligència Artificial - CSIC)
Filippo Bistaffa (Institut d'Investigació en Intel·ligència Artificial - CSIC)
Roel I.J. Dobbe (TU Delft - Technology, Policy and Management)
Catholijn M. Jonker (Universiteit Leiden, TU Delft - Electrical Engineering, Mathematics and Computer Science)
Maite Lopez-Sanchez (University of Barcelona)
Juan A. Rodriguez-Aguilar (Institut d'Investigació en Intel·ligència Artificial - CSIC)
Pradeep K. Murukannaiah (TU Delft - Electrical Engineering, Mathematics and Computer Science)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
As artificial agents become increasingly embedded in our society, we must ensure that their behavior aligns with human values. Value alignment entails value inference, the process of identifying values and reasoning about how humans prioritize values. We introduce a holistic framework that connects the technical (AI) components necessary for value inference. Subsequently, we discuss how hybrid intelligence'the synergy of human and artificial intelligence'is instrumental to the success of value inference. Finally, we illustrate how value inference both poses significant challenges and provides novel opportunities for multiagent systems research.