Moral Decision Making Frameworks for Artificial Intelligence

Conference Paper

The generality of decision and game theory has enabled domain-independent progress in AI research. For example, a better algorithm for finding good policies in (PO)MDPs can be instantly used in a variety of applications. But such a general theory is lacking when it comes to moral decision making. For AI applications with a moral component, are we then forced to build systems based on many ad-hoc rules? In this paper we discuss possible ways to avoid this conclusion.

Duke Authors

Cited Authors

  • Conitzer, V; Sinnott-Armstrong, W; Schaich Borg, J; Deng, Y; Kramer, M

Conference Name

  • Conference on Artificial Intelligence (AAAI-17)

Conference Start Date

  • 2017