Ethical Judgment of Agents’ Behaviors in Multi-Agent Systems

International audienceThe increasing use of multi-agent technologies in various areasraises the necessity of designing agents that judge ethicalbehaviors in context. This is why several works integrateethical concepts in agents’ decision making processes. However,those approaches consider mainly an agent-centeredperspective, letting aside the fact that agents are in interactionwith other artificial agents or human beings that canuse other ethical concepts. In this article, we address theproblem of producing ethical behaviors from a multi-agentperspective. To this end, we propose a model of ethical judgmentan agent can use in order to judge the ethical dimensionof both its own behavior and the other agents’ behaviors.This model is based on a rationalist and explicit approachthat distinguishes theory of good and theory of right. Aproof-of-concept implemented in Answer Set Programmingand based on a simple scenario is given to illustrate thosefunctionalities