Cognitive Agents Learning by Communicating - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier
Conference Papers Year : 2003

Cognitive Agents Learning by Communicating

Abstract

Cognitive Agent communication is a research field in full development. We propose here an extension and an implementation of the STROBE model, which regards the Agents as Scheme interpreters. These Agents are able to interpret messages in a dedicated environment including an interpreter that learns from the current conversation. These interpreters evolve dynamically, progressively with the conversations, and thus represent evolving meta level Agent knowledge. We illustrate this theoretical model by a “teacher-student” dialogue experimentation, where an Agent learns a new performative at the completion of the conversation. Details of the implementation are not provided here, but are available.
Fichier principal
Vignette du fichier
D170.PDF (59.09 Ko) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

lirmm-00191962 , version 1 (26-11-2007)

Identifiers

  • HAL Id : lirmm-00191962 , version 1

Cite

Clement Jonquet, Stefano A. Cerri. Cognitive Agents Learning by Communicating. ALCAA: Agents Logiciels - Coopération - Apprentissage - Activités Humaines, Sep 2003, Bayonne, France. ⟨lirmm-00191962⟩
238 View
134 Download

Share

More