The surprising capabilities demonstrated by AI technologies overlaid on detailed data and fine-grained control give cause for concern that agents can wield enormous power over human welfare, drawing increasing attention to ethics in AI.
Ethics is inherently a multiagent concern an amalgam of (1) one party's concern for another and (2) a notion of justice. To capture the multiagent conception, this tutorial introduces ethics as a sociotechnical construct. Specifically, we demonstrate how ethics can be modeled and analyzed, and requirements on ethics (value preferences) can be elicited, in a sociotechnical system (STS). An STS comprises of autonomous social entities (principals, i.e., people and organizations), and technical entities (agents, who help principals), and resources (e.g., data, services, sensors, and actuators).
This tutorial includes three key elements. (1) Specifying a decentralized STS, representing ethical postures of individual agents as well as the systemic (STS level) ethical posture. (2) Reasoning about ethics, including how individual agents can select actions that align with the ethical postures of all concerned principals. (3) Eliciting value preferences (which capture ethical requirements) of stakeholders using a value-based negotiation technique.
We build upon our earlier tutorials (e.g., at AAMAS 2015 and IJCAI 2016) on engineering decentralized MAS, which were well attended. However, we extend the previous tutorials substantially, including ideas on ethics and values. Attendees will learn the theoretical foundations as well as how to apply those foundations to systematically engineer an ethical STS.
Motivation: Ethical sociotechnical systems
Foundations
Background on ethics (virtue, utilitarianism, Rawls . . . )
Laws, norms, privacy
Preferences and values (Rokeach, Schwartz)
Techniques
Specifying an ethical STS
Reasoning about ethics
Value-based negotiation
Research Directions
Verification and simulation
Emotions and equity, and language
Elicitation (surveys; active value learning; inverse RL)
Rethinking fairness, accountability, and transparency
Law and consent
Synthesis: Summary and concluding remarks
Pradeep Murukannaiah (Delft University of Technology)
Nirav Ajmeri (North Carolina State University)
Munindar P. Singh (North Carolina State University)
Tutorial video (requires (free) registration on Underline.io)