Search
 
loader loading subjects...
cover
Norm Compliance in Reinforcement Learning Agents via Restraining Bolts
Emery A. Neufeld, Agata Ciabattoni, Radu Florin Tulcan
119 - 130
10.3233/FAIA241239
Research Article
Frontiers in Artificial Intelligence and Applications
Volume 395: Legal Knowledge and Information Systems
Abstract

We modify the restraining bolt technique, originally designed for safe reinforcement learning, to regulate agent behavior in alignment with social, ethical, and legal norms. Rather than maximizing rewards for norm compliance, our approach minimizes penalties for norm violations. We demonstrate in case studies the effectiveness of our approach in capturing benchmark challenges in normative reasoning like contrary-to-duty obligations, exceptions, and temporal obligations.

Download
Creative Commons License