Modular self-organization for a long-living autonomous agent - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports Year : 2003

Modular self-organization for a long-living autonomous agent

Bruno Scherrer

Abstract

The aim of this paper is to provide a sound framework for addressing a difficult problem: the automatic construction of an autonomous agent's modular architecture. We combine results from two apparently uncorrelated domains: Autonomous planning through Markov Decision Processes and a General Data Clustering Approach using a kernel-like method. Our fundamental idea is that the former is a good framework for addressing autonomy whereas the latter allows to tackle self-organizing problems. Indeed, we derive a modular self-organizing algorithm in which an autonomous agent learns to efficiently spread $n$ planning problems over m initially blank modules.
Fichier principal
Vignette du fichier
A03-R-053.pdf (261.13 Ko) Télécharger le fichier
Loading...

Dates and versions

inria-00107753 , version 1 (19-10-2006)

Identifiers

  • HAL Id : inria-00107753 , version 1

Cite

Bruno Scherrer. Modular self-organization for a long-living autonomous agent. [Intern report] A03-R-053 || scherrer03b, 2003, 7 p. ⟨inria-00107753⟩
281 View
29 Download

Share

Gmail Facebook Twitter LinkedIn More