Moral Decision Making Frameworks for Artificial Intelligence

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.

[1]  I. Watson,et al.  Moral preferences , 2016 .

[2]  J. Haidt,et al.  Intuitive ethics: how innately prepared intuitions generate culturally variable virtues , 2004, Daedalus.

[3]  Bernard Gert,et al.  Common Morality: Deciding What to Do , 2004 .

[4]  Marcello Guarini,et al.  Particularism and the Classification and Reclassification of Moral Cases , 2006, IEEE Intelligent Systems.

[5]  M. Dufwenberg.  Game theory. , 2011, Wiley interdisciplinary reviews. Cognitive science.

[6]  John Mikhail,et al.  Universal moral grammar: theory, evidence and the future , 2007, Trends in Cognitive Sciences.

[7]  F. Brandt,et al.  Computational Social Choice: Prospects and Challenges , 2011, FET.

[8]  Joyce E. Berg,et al.  Trust, Reciprocity, and Social History , 1995 .

[9]  Iyad Rahwan,et al.  The social dilemma of autonomous vehicles , 2015, Science.

[10]  Tuomas Sandholm,et al.  FutureMatch: Combining Human Value Judgments and Machine Learning to Match in Dynamic Environments , 2015, AAAI.

[11]  R. Cabeza,et al.  Moral foundations vignettes: a standardized stimulus database of scenarios based on moral foundations theory , 2015, Behavior research methods.

[12]  Fabio Pianesi,et al.  Ethical Dilemmas for Adaptive Persuasion Systems , 2016, AAAI.

[13]  Francesca Rossi,et al.  Embedding Ethical Principles in Collective Decision Support Systems , 2016, AAAI.

[14]  R Fox,et al.  Moral dilemmas. , 1998, Journal of the Royal Society of Medicine.

[15]  J. Horvat.  THE ETHICS OF ARTIFICIAL INTELLIGENCE , 2016 .

[16]  Vincent Conitzer,et al.  An "Ethical" Game-Theoretic Solution Concept for Two-Player Perfect-Information Games , 2008, WINE.

[17]  A. Tversky,et al.  Choices, Values, and Frames , 2000 .

[18]  Vincent Conitzer,et al.  Handbook of Computational Social Choice , 2016 .

[19]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[20]  James H. Moor,et al.  The Nature, Importance, and Difficulty of Machine Ethics , 2006, IEEE Intelligent Systems.

[21]  C. Allen,et al.  Moral Machines: Teaching Robots Right from Wrong , 2008 .

[22]  Walter Sinnott-Armstrong,et al.  Framing moral intuitions. , 2008 .

[23]  Colin Camerer.  Behavioral Game Theory: Experiments in Strategic Interaction , 2003 .

[24]  Michael Anderson,et al.  Machine Ethics: Creating an Ethical Intelligent Agent , 2007, AI Mag..