Skip to Main content Skip to Navigation
Conference papers

Approche multi-agent combinant raisonnement et apprentissage pour un comportement éthique

Abstract : The need to imbue Artificial Intelligence algorithms with ethical considerations is more and more present. Combining reasoning and learning, this paper proposes a hybrid method, where judging agents evaluate the ethics of learning agents' behavior. The aim is to improve the ethics of their behavior in dynamic multi-agent environements. Several advantages ensue from this separation: possibility of co-construction between agents and humans; judging agents more accessible for non-experts humans; adoption of several points of view to judge the same agent, producing a richer feedback. Experiments on energy distribution inside a Smart Grid simulator show the learning agents' ability to comply with judging agents' rules, including when they evolve.
Complete list of metadata
Contributor : Florent Breuil Connect in order to contact the contributor
Submitted on : Monday, November 8, 2021 - 3:31:33 PM
Last modification on : Tuesday, January 4, 2022 - 6:49:52 AM


2021 Approche multi-agent comb...
Files produced by the author(s)


  • HAL Id : emse-03278353, version 1


Rémy Chaput, Jérémy Duval, Olivier Boissier, Mathieu Guillermin, Salima Hassas. Approche multi-agent combinant raisonnement et apprentissage pour un comportement éthique. Journées Francophones sur les Systèmes Multi-Agents, Jun 2021, Bordeaux, France. ⟨emse-03278353⟩



Les métriques sont temporairement indisponibles