Un modèle de mémoire pour l'apprentissage de communication dans un SMA

Abstract : Learning in a multi-agent context is a difficult task, especially since the communication with other agents require additional information to be stored and used in the learning process. In this paper, we propose a model of agent memory for command and control in a multi-agent context. We first show why the existing memory models are not sufficient to support automated learning of command and control in a multi-agent context. Then, we describe our model for storing messages and answers. Finally we show on an example that this model allows faster learning and better convergence.
Complete list of metadatas

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01852263
Contributor : Limsi Publications <>
Submitted on : Wednesday, August 1, 2018 - 11:29:29 AM
Last modification on : Monday, September 16, 2019 - 11:45:57 AM
Long-term archiving on : Friday, November 2, 2018 - 1:54:00 PM

File

jfsma2013-hoet.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01852263, version 1

Citation

Shirley Hoet, Nicolas Sabouret. Un modèle de mémoire pour l'apprentissage de communication dans un SMA. Journées Francophones sur les Systèmes Multi-Agents (JFSMA 2013), Jul 2013, Lille, France. ⟨hal-01852263⟩

Share

Metrics

Record views

35

Files downloads

14