Moral Decision Making Frameworks for Artificial Intelligence

Authors

  • Vincent Conitzer Duke University
  • Walter Sinnott-Armstrong Duke University
  • Jana Schaich Borg Duke University
  • Yuan Deng Duke University
  • Max Kramer Duke University

DOI:

https://doi.org/10.1609/aaai.v31i1.11140

Keywords:

moral AI, game theory, machine learning

Abstract

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.

Downloads

Published

2017-02-12

How to Cite

Conitzer, V., Sinnott-Armstrong, W., Schaich Borg, J., Deng, Y., & Kramer, M. (2017). Moral Decision Making Frameworks for Artificial Intelligence. Proceedings of the AAAI Conference on Artificial Intelligence, 31(1). https://doi.org/10.1609/aaai.v31i1.11140