Self-Adaptive Aided Decision-Making using a Multi-Agent System

Nicolas Brax (1) , Éric Andonoff (1) , Marie-Pierre Gleizes (1) , Pierre Glize (1)

1 IRIT-SMAC - Systèmes Multi-Agents Coopératifs

Information required for decision-making in complex applications, such as flood forecast or maritime surveillance, can be represented using a mathematical function. However, due to the complexity of the considered applications and their dynamics, the parameters involved in the mathematical function can be hard to value a priori. This paper presents a Multi-Agent System, called PaMAS (Parameter Multi-Agent System) that is able to learn such parameters values on the fly, autonomously, cooperatively and by self-adaptation. It also illustrates the application of PaMAS in the context of the maritime surveillance European project I2C. It finally provides an evaluation of the PaMAS learning.

Mots clés: Multi-agent System; Learning; Self-adaptation; Decision Making; Maritime Surveillance

Domaines: Apprentissage [cs.LG]; Système multi-agents [cs.MA]

Nicolas Brax, Éric Andonoff, Marie-Pierre Gleizes, Pierre Glize. Self-Adaptive Aided Decision-Making using a Multi-Agent System. 5th International Conference on Agents and Artificial Intelligence (ICAART 2013), Feb 2013, Barcelona, Spain. pp.419-422. ⟨hal-03669167⟩