Moral Artificial Intelligence and the Societal Tradeoffs Problem

Vincent Conitzer - Duke University

Dec. 15, 2016, 2 p.m. - Dec. 15, 2016, 3 p.m.

ARTS 215


AI systems increasingly need to make decisions with a moral component. Should a self-driving car prioritize the safety of its passengers over that of others, and to what extent?  Should an algorithm that decides which donors and patients to match in a kidney exchange take features such as the patient's age into account, and to what extent?  I will briefly discuss two approaches to these problems: extending game-theoretic frameworks, and learning from examples of human decisions. Under the second approach, we will generally find that not all humans agree!  How, then, should we aggregate their judgments to make coherent decisions? This is a problem in computational social choice. I will present our work on the ``societal tradeoffs'' problem in which, based on multiple human judgments, we aim to find a specific value for x in statements such as ``using one gallon of gasoline is as bad as creating x bags of landfill trash.'' The first part (https://www.cs.duke.edu/~conitzer/moralAAAI17.pdf) is joint work with Walter Sinnott-Armstrong, Jana Schaich Borg, Yuan Deng, and Max Kramer, and the second part (https://www.cs.duke.edu/~conitzer/tradeoffsAAAI16.pdf) with Rupert Freeman, Markus Brill, and Yuqian Li.)

Vincent Conitzer is the Kimberly J. Jenkins University Professor of New Technologies and Professor of Computer Science, Professor of Economics, and Professor of Philosophy at Duke University. He received Ph.D. (2006) and M.S. (2003) degrees in Computer Science from Carnegie Mellon University, and an A.B. (2001) degree in Applied Mathematics from Harvard University. Most of his research is on artificial intelligence (especially multiagent systems) and economic theory (especially game theory, social choice, and mechanism design). Conitzer has received the Social Choice and Welfare Prize, a Presidential Early Career Award for Scientists and Engineers (PECASE), the IJCAI Computers and Thought Award, an NSF CAREER award, the inaugural Victor Lesser dissertation award, an honorable mention for the ACM dissertation award, and several awards for papers and service at the AAAI and AAMAS conferences. He has also been named a Guggenheim Fellow, a Kavli Fellow, a Bass Fellow, a Sloan Fellow, and one of AI's Ten to Watch. Conitzer and Preston McAfee are the founding Editors-in-Chief of the ACM Transactions on Economics and Computation (TEAC).