<div class="csl-bib-body">
<div class="csl-entry">Neufeld, E., Ciabattoni, A., & Tulcan, R. F. (2024). Norm Compliance in Reinforcement Learning Agents via Restraining Bolts. In J. Savelka, J. Harasta, T. Novotna, & J. Misek (Eds.), <i>Legal Knowledge and Information Systems</i> (pp. 119–130). https://doi.org/10.3233/FAIA241239</div>
</div>
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/209776
-
dc.description.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.
en
dc.description.sponsorship
European Commission
-
dc.language.iso
en
-
dc.relation.ispartofseries
Frontiers in artificial intelligence and applications : FAIA
-
dc.rights.uri
https://creativecommons.org/licenses/by-nc/4.0/
-
dc.subject
ethical reinforcement learning
en
dc.subject
safe reinforcement learning
en
dc.subject
LTL over finite traces
en
dc.title
Norm Compliance in Reinforcement Learning Agents via Restraining Bolts
en
dc.type
Inproceedings
en
dc.type
Konferenzbeitrag
de
dc.rights.license
Creative Commons Namensnennung - Nicht kommerziell 4.0 International
de
dc.rights.license
Creative Commons Attribution-NonCommercial 4.0 International
