Deontic Paradoxes in ASP with Weak Constraints
This work addresses the problem of efficient computational tools for normative reasoning in AI, which is crucial for applications sensitive to legal, social, and ethical norms, though it is incremental as it builds on existing ASP methods.
The paper tackled the challenge of normative reasoning for AI decision-making by using Answer Set Programming (ASP) with weak constraints to encode and resolve deontic paradoxes, achieving ethically preferable results in an ethical Pac-man application with comparable performance to related works.
The rise of powerful AI technology for a range of applications that are sensitive to legal, social, and ethical norms demands decision-making support in presence of norms and regulations. Normative reasoning is the realm of deontic logics, that are challenged by well-known benchmark problems (deontic paradoxes), and lack efficient computational tools. In this paper, we use Answer Set Programming (ASP) for addressing these shortcomings and showcase how to encode and resolve several well-known deontic paradoxes utilizing weak constraints. By abstracting and generalizing this encoding, we present a methodology for translating normative systems in ASP with weak constraints. This methodology is applied to "ethical" versions of Pac-man, where we obtain a comparable performance with related works, but ethically preferable results.