Have a break from making decisions, have a MARS: The Multi-valued Action Reasoning System
This work addresses the problem of implementing ethical reasoning in artificial agents, which is incremental as it builds on existing value-based decision-making frameworks.
The paper introduces the Multi-valued Action Reasoning System (MARS), an automated model for ethical decision-making in AI that identifies preferred actions based on moral paradigms, and demonstrates its application in modeling ethical theories and moral dilemmas.
The Multi-valued Action Reasoning System (MARS) is an automated value-based ethical decision-making model for artificial agents (AI). Given a set of available actions and an underlying moral paradigm, by employing MARS one can identify the ethically preferred action. It can be used to implement and model different ethical theories, different moral paradigms, as well as combinations of such, in the context of automated practical reasoning and normative decision analysis. It can also be used to model moral dilemmas and discover the moral paradigms that result in the desired outcomes therein. In this paper, we give a condensed description of MARS, explain its uses, and comparatively place it in the existing literature.