Modular self-organization for a long-living autonomous agent

Bruno Scherrer 1
1 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
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.
Document type :
Reports
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.inria.fr/inria-00107753
Contributor : Publications Loria <>
Submitted on : Thursday, October 19, 2006 - 9:07:59 AM
Last modification on : Thursday, January 11, 2018 - 6:19:48 AM
Long-term archiving on : Friday, November 25, 2016 - 12:39:53 PM

Identifiers

  • HAL Id : inria-00107753, version 1

Collections

Citation

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

Share

Metrics

Record views

426

Files downloads

43