Moral Decision Making Frameworks for Artificial Intelligence

Vincent Conitzer, Walter Sinnott-Armstrong, Jana Schaich Borg, Yuan Deng, Max Kramer

AAAI 2017 pp. 4831-4835

doi:10.1609/AAAI.V31I1.11140 /aaai/2017/conitzer2017aaai-moral/

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.

PDF AAAI Semantic Scholar

Cite

Text

Conitzer et al. "Moral Decision Making Frameworks for Artificial Intelligence." AAAI Conference on Artificial Intelligence, 2017. doi:10.1609/AAAI.V31I1.11140

Markdown

[Conitzer et al. "Moral Decision Making Frameworks for Artificial Intelligence." AAAI Conference on Artificial Intelligence, 2017.](https://mlanthology.org/aaai/2017/conitzer2017aaai-moral/) doi:10.1609/AAAI.V31I1.11140

BibTeX

@inproceedings{conitzer2017aaai-moral,
  title     = {{Moral Decision Making Frameworks for Artificial Intelligence}},
  author    = {Conitzer, Vincent and Sinnott-Armstrong, Walter and Borg, Jana Schaich and Deng, Yuan and Kramer, Max},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {4831-4835},
  doi       = {10.1609/AAAI.V31I1.11140},
  url       = {https://mlanthology.org/aaai/2017/conitzer2017aaai-moral/}
}