A Voting-Based System for Ethical Decision Making
arXiv:1709.06692
Abstract
We present a general approach to automating ethical decisions, drawing on machine learning and computational social choice. In a nutshell, we propose to learn a model of societal preferences, and, when faced with a specific ethical dilemma at runtime, efficiently aggregate those preferences to identify a desirable choice. We provide a concrete algorithm that instantiates our approach; some of its crucial steps are informed by a new theory of swap-dominance efficient voting rules. Finally, we implement and evaluate a system for ethical decision making in the autonomous vehicle domain, using preference data collected from 1.3 million people through the Moral Machine website.
25 pages; paper has been reorganized, related work and discussion sections have been expanded
Cited by in corpus (8)
- Adapting a Kidney Exchange Algorithm to Align with Human Values
- Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning
- Envy-Free Classification
- The Smoothed Possibility of Social Choice
- Making the Cut: A Bandit-based Approach to Tiered Interviewing
- Kidney Exchange with Inhomogeneous Edge Existence Uncertainty
- Strategyproof Learning: Building Trustworthy User-Generated Datasets
- A Roadmap for Robust End-to-End Alignment