Limitations of adaptive critic control schemes

W.T.C. van Luenen, P.J. de Jager, J. van Amerongen, H.M. Franken

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Abstract

    Earlier publications about learning control systems used adaptive critic schemes. We argue that the results published about adaptive critic schemes in control problems appeared positive due to the choice of the inverted pendulum or cart-pole system as a test case. This conclusion was drawn after e xamination of a number of publications and after our experiments with the original adaptive critic scheme. In this paper we describe an adaptive critic scheme derived from a control point of view. This scheme allows us to indicate more clearly the limitations of the scheme in a control context. We show how an adaptive critic scheme fails to learn a set-point control for a simple second order non-linear process in a simulation.
    Original languageEnglish
    Title of host publicationICANN ’93
    Subtitle of host publicationProceedings of the International Conference on Artificial Neural Networks Amsterdam, The Netherlands 13–16 September 1993
    EditorsStan Gielen, Bert Kappen
    Place of PublicationLondon
    PublisherSpringer
    Pages810-813
    Number of pages4
    ISBN (Electronic)978-1-4471-2063-6
    ISBN (Print)978-3-540-19839-0
    DOIs
    Publication statusPublished - 13 Sept 1993
    EventInternational Conference on Artificial Neural Networks, ICANN 1993 - Amsterdam, Netherlands
    Duration: 13 Sept 199316 Sept 1993

    Conference

    ConferenceInternational Conference on Artificial Neural Networks, ICANN 1993
    Abbreviated titleICANN
    Country/TerritoryNetherlands
    CityAmsterdam
    Period13/09/9316/09/93

    Keywords

    • Inverted pendulum
    • Criterion surface
    • Flat region
    • State feedback controller
    • Criterion predictor

    Fingerprint

    Dive into the research topics of 'Limitations of adaptive critic control schemes'. Together they form a unique fingerprint.

    Cite this