Moral decision making frameworks for artificial intelligence
Publication
, Conference
Conitzer, V; Sinnott-Armstrong, W; Borg, JS; Deng, Y; Kramer, M
Published in: International Symposium on Artificial Intelligence and Mathematics, ISAIM 2018
January 1, 2018
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 Scholars
Published In
International Symposium on Artificial Intelligence and Mathematics, ISAIM 2018
Publication Date
January 1, 2018
Citation
APA
Chicago
ICMJE
MLA
NLM
Conitzer, V., Sinnott-Armstrong, W., Borg, J. S., Deng, Y., & Kramer, M. (2018). Moral decision making frameworks for artificial intelligence. In International Symposium on Artificial Intelligence and Mathematics, ISAIM 2018.
Conitzer, V., W. Sinnott-Armstrong, J. S. Borg, Y. Deng, and M. Kramer. “Moral decision making frameworks for artificial intelligence.” In International Symposium on Artificial Intelligence and Mathematics, ISAIM 2018, 2018.
Conitzer V, Sinnott-Armstrong W, Borg JS, Deng Y, Kramer M. Moral decision making frameworks for artificial intelligence. In: International Symposium on Artificial Intelligence and Mathematics, ISAIM 2018. 2018.
Conitzer, V., et al. “Moral decision making frameworks for artificial intelligence.” International Symposium on Artificial Intelligence and Mathematics, ISAIM 2018, 2018.
Conitzer V, Sinnott-Armstrong W, Borg JS, Deng Y, Kramer M. Moral decision making frameworks for artificial intelligence. International Symposium on Artificial Intelligence and Mathematics, ISAIM 2018. 2018.
Published In
International Symposium on Artificial Intelligence and Mathematics, ISAIM 2018
Publication Date
January 1, 2018