<div class="csl-bib-body">
<div class="csl-entry">Neufeld, E. A., Bartocci, E., Ciabattoni, A., & Governatori, G. (2022). Enforcing ethical goals over reinforcement-learning policies. <i>Ethics and Information Technology</i>, <i>24</i>(4), Article 43. https://doi.org/10.1007/s10676-022-09665-8</div>
</div>
-
dc.identifier.issn
1388-1957
-
dc.identifier.uri
http://hdl.handle.net/20.500.12708/101894
-
dc.description.abstract
Recent years have yielded many discussions on how to endow autonomous agents with the ability to make ethical decisions, and the need for explicit ethical reasoning and transparency is a persistent theme in this literature. We present a modular and transparent approach to equip autonomous agents with the ability to comply with ethical prescriptions, while still enacting pre-learned optimal behaviour. Our approach relies on a normative supervisor module, that integrates a theorem prover for defeasible deontic logic within the control loop of a reinforcement learning agent. The supervisor operates as both an event recorder and an on-the-fly compliance checker w.r.t. an external norm base. We successfully evaluated our approach with several tests using variations of the game Pac-Man, subject to a variety of “ethical” constraints.
en
dc.description.sponsorship
WWTF Wiener Wissenschafts-, Forschu und Technologiefonds
-
dc.language.iso
en
-
dc.publisher
Springer
-
dc.relation.ispartof
Ethics and Information Technology
-
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
-
dc.subject
Deontic defeasible logic
en
dc.subject
Ethical artificial intelligence
en
dc.subject
Normative reasoning
en
dc.subject
Reinforcement learning
en
dc.title
Enforcing ethical goals over reinforcement-learning policies