Inferring Values via Hybrid Intelligence
Enrico Liscio (TU Delft - Interactive Intelligence)
Roger Lera-Leri (Artificial Intelligence Research Institute, Spanish National Scientific Research Council)
Filippo Bistaffa (Artificial Intelligence Research Institute, Spanish National Scientific Research Council)
R. I.J. Dobbe (TU Delft - Information and Communication Technology)
C.M. Jonker (Universiteit Leiden, TU Delft - Interactive Intelligence)
Maite Lopez-Sanchez (Universitat Politecnica de Catalunya)
Juan A. Rodriguez-Aguilar (Artificial Intelligence Research Institute, Spanish National Scientific Research Council)
Pradeep Murukannaiah (TU Delft - Interactive Intelligence)
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
Values, such as freedom and safety, are the core motivations that guide us humans. A prerequisite for creating value-aligned multiagent systems that involve humans and artificial agents is value inference, the process of identifying values and reasoning about human value preferences. We introduce a framework that connects the value inference steps, and motivate why a hybrid intelligence approach is instrumental for its success. We also highlight the multidisciplinary research challenges that hybrid value inference entails.
help_outline