Published March 1, 2023 | Version v1
Software Open

AJAR: An Argumentation-based Judging Agents Framework for Ethical Reinforcement Learning

Authors/Creators

  • 1. University of Luxembourg
  • 2. Mines Saint-Etienne, Univ Clermont Auvergne, CNRS, UMR 6158 LIMOS, Institut Henri Fayol
  • 3. Univ Lyon, UCBL, CNRS, INSA Lyon, LIRIS, UMR5205
  • 4. Inria, Université Côte d'Azur, CNRS, I3S

Description

An open-source implementation of AJAR (Argumentation-based Judging Agents Framework for ethical Reinforcement learning), on a multi-agent Smart Grid simulator of energy distribution.

Notes

The data included in this simulator is a property of and licensed by OpenEI (https://doi.org/10.25984/1788456, CC-BY-4.0). This work is partially funded by the French Région Auvergne Rhônes-Alpes (AURA), as part of the Ethics.AI project (Pack Ambition Recherche), and by the Luxembourg National Research Fund under Grant No. IS/14717072. We gratefully acknowledge support from the CNRS/IN2P3 Computing Center (Lyon — France) for providing computing and data-processing resources.

Files

AJAR.zip

Files (110.7 kB)

Name Size Download all
md5:b395d0d3c1dbb5ce719277cd43347423
110.7 kB Preview Download