Éthique collective dans les systèmes multi-agents

  title={{\'E}thique collective dans les syst{\`e}mes multi-agents},
  author={Nicolas Cointe and Gr{\'e}gory Bonnet and Olivier Boissier},
  journal={Rev. d'Intelligence Artif.},
L’utilisation croissante des technologies multi-agents pour le developpement de systemes socio-techniques revele de nombreux verrous, dont ceux lies a l’ethique des decisions autonomes que de tels systemes peuvent etre amenes a prendre. Ces verrous sont souvent consideres comme un probleme de conception selon une perspective centree sur l’agent. Ici, nous elargissons cette perspective au collectif, introduisant ainsi les questions ethiques decoulant de la participation des agents autonomes a… 

Figures from this paper

Jugement éthique pour la décision et la coopération dans les systèmes multi-agents

L’usage croissant des systemes multi-agents dans divers domaines d’application souleve la necessite de concevoir des agents capables de prendre des decisions s’appuyant sur des principes ethiques.

Fiabilité, honnêteté et éthique dans les systèmes d'agents autonomes. (Reliability, honesty and ethics in systems of autonomous agents)

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not, for teaching and research institutions in France or abroad, or from public or private research centers.

Optimized Drug Distribution for Pharmacies of the National Order of Pharmacists in DR Congo using a Multi-Agent Engineering Approach

The design of a Multi-Agent System (MAS) is focused on in order to help the PCOP to control the pharmaceutical activity on the one hand, and the pharmacists to sell their drugs safely on the other.



Éthique de la recherche en robotique

La robotique, comme plus largement le numerique, debouche sur de multiples usages aux deploiements parfois aussi massifs qu’inattendus, tel l’essor actuel des drones civils. Dans ce contexte

Ethical Judgment of Agents' Behaviors in Multi-Agent Systems

A model of ethical judgment an agent can use in order to judge the ethical dimension of both its own behavior and the other agents' behaviors is proposed, based on a rationalist and explicit approach that distinguishes theory of good and theory of right.

The pursuit of computational justice in open systems

It is argued that some answers to justice questions can be found in the formal characterisation of different aspects of ‘justice’ and that these different aspects need a principled operationalisation as policies for system management.

Multi-Agent Based Ethical Asset Management

This article proposes an approach to represent morals and ethics in a BDI architecture and illustrates its use in the context of ethical asset management.

Towards a formal framework for the search of a consensus between autonomous agents

A general formal framework for dialogue between autonomous agents which are looking for a common agreement about a collective choice is proposed and properties of the framework are studied.

BDI Agents: From Theory to Practice

This paper explores a particular type of rational agent, a BeliefDesire-Intention (BDI) agent, and integrates the theoretical foundations of BDI agents from both a quantitative decision-theoretic perspective and a symbolic reasoning perspective.

Les Systèmes multi-agents: vers une intelligence collective

entity Concrete entity

On the Operationality of Moral-Sense Decision Making

The proposal of a new architecture is supported on the clarification of the organization and structure of an agent, ie.

Toward ensuring ethical behavior from autonomous systems: a case-supported principle-based paradigm

It is argued that ethically significant behavior of autonomous systems can be guided by explicit ethical principles abstracted from a consensus of ethicists.

The evolution of cooperation.

A model is developed based on the concept of an evolutionarily stable strategy in the context of the Prisoner's Dilemma game to show how cooperation based on reciprocity can get started in an asocial world, can thrive while interacting with a wide range of other strategies, and can resist invasion once fully established.