Etude de différentes combinaisons de comportements adaptatives. - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle Year : 2006

Etude de différentes combinaisons de comportements adaptatives.

Abstract

This article focusses on the automated synthesis of agents in an uncertain environment, working in the setting of Reinforcement Learning, and more precisely of Partially Observable Markov Decision Processes. The agents (with no model of their environment and no short-term memory) are facing multiple motivations/goals simultaneously, a problem related to the field of Action Selection. We propose and evaluate various Action Selection architectures. They all combine already known basic behaviors in an adaptive manner, by learning the tuning of the combination, so as to maximize the agent's payoff. %This work opens the way to a second step in which the basic behaviors themselves will be selected and designed in an automated manner. The logical continuation of this work is to automate the selection and design of the basic behaviors themselves.
Fichier principal
Vignette du fichier
buffet_etudeCombComportement_RIA06.pdf (267.05 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

inria-00119272 , version 1 (08-12-2006)

Identifiers

  • HAL Id : inria-00119272 , version 1

Cite

Olivier Buffet, Alain Dutech, François Charpillet. Etude de différentes combinaisons de comportements adaptatives.. Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle, 2006, Décision et planification dans l'incertain, 20 (2-3), pp.311-344. ⟨inria-00119272⟩
189 View
197 Download

Share

Gmail Facebook X LinkedIn More