Etude de différentes combinaisons de comportements adaptatives

Translated title of the contribution: Study of various adaptative combinations of behaviors

Olivier Buffet*, Alain Dutech, François Charpillet

*Corresponding author for this work

    Research output: Contribution to journalArticlepeer-review

    2 Citations (Scopus)

    Abstract

    This article focussei 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 thefield 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. The logical continuation of this work is to automate the selection and design of the basic behaviors themselves.

    Translated title of the contributionStudy of various adaptative combinations of behaviors
    Original languageFrench
    Pages (from-to)311-343
    Number of pages33
    JournalRevue d'Intelligence Artificielle
    Volume20
    Issue number2-3
    DOIs
    Publication statusPublished - 2006

    Fingerprint

    Dive into the research topics of 'Study of various adaptative combinations of behaviors'. Together they form a unique fingerprint.

    Cite this