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. |
Year | Venue | DocType |
---|---|---|
2018 | THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE | Conference |
Citations | PageRank | References |
5 | 0.50 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vincent Conitzer | 1 | 10 | 2.71 |
Walter Sinnott-Armstrong | 2 | 7 | 1.60 |
Jana Schaich Borg | 3 | 51 | 12.96 |
Yuan Deng | 4 | 25 | 11.91 |
Max Kramer | 5 | 5 | 0.50 |