Conference paper by Vincent Conitzer, Walter Sinnott-Armstrong, Jana Schaich Borg, Yuan Deng and Max Kramer. Presented at ISAIM 2018 – The International Symposium on Artificial Intelligence and Mathematics. Special Session on Formalising Robot Ethics.
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.