Dynamic Scripting with Team Coordination in Air Combat Simulation

A. Toubman, Jan Joris Roessingh, P.H.M. Spronck, A. Plaat, H.J. van den Herik

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

    Abstract

    Traditionally, behavior of Computer Generated Forces (CGFs) is controlled through scripts. Building such scripts requires time and expertise, and becomes harder as the domain becomes richer and more life-like. These downsides can be reduced by automatically generating behavior for CGFs using machine learning techniques. This paper focuses on Dynamic Scripting (DS), a technique tailored to generating agent behavior. DS searches for an optimal combination of rules from a rule base. Under the assumption that intra-team coordination leads to more effective learning, we propose an extension of DS, called DS+C, with explicit coordination. In a comparison with regular DS we find that the addition of team coordination results in earlier convergence to optimal behavior. In addition, we achieved a performance increase of 20% against an unpredictable opponent. With DS+C, behavior for CGFs can be generated that is more effective since the CGFs act on knowledge achieved by coordination and the behavior converges more efficiently than with regular DS.
    Original languageEnglish
    Title of host publicationModern Advances in Applied Intelligence Lecture Notes in Computer Science
    Subtitle of host publication27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2014 Proceedings, Part I
    PublisherSpringer International Publishing
    Pages440-449
    Number of pages10
    Volume8481
    Edition27
    ISBN (Electronic)9783319074559
    ISBN (Print)9783319074542
    Publication statusPublished - 2014
    Event27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2014 - Kaohsiung, Taiwan, Province of China
    Duration: 3 Jun 20146 Jun 2014

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer Link
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349

    Conference

    Conference27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2014
    CountryTaiwan, Province of China
    CityKaohsiung
    Period3/06/146/06/14

    Fingerprint

    Air
    Learning systems

    Cite this

    Toubman, A., Roessingh, J. J., Spronck, P. H. M., Plaat, A., & van den Herik, H. J. (2014). Dynamic Scripting with Team Coordination in Air Combat Simulation. In Modern Advances in Applied Intelligence Lecture Notes in Computer Science: 27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2014 Proceedings, Part I (27 ed., Vol. 8481, pp. 440-449 ). (Lecture Notes in Computer Science). Springer International Publishing.
    Toubman, A. ; Roessingh, Jan Joris ; Spronck, P.H.M. ; Plaat, A. ; van den Herik, H.J. / Dynamic Scripting with Team Coordination in Air Combat Simulation. Modern Advances in Applied Intelligence Lecture Notes in Computer Science: 27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2014 Proceedings, Part I. Vol. 8481 27. ed. Springer International Publishing, 2014. pp. 440-449 (Lecture Notes in Computer Science).
    @inproceedings{7610571b2e514b25a1131184ff848316,
    title = "Dynamic Scripting with Team Coordination in Air Combat Simulation",
    abstract = "Traditionally, behavior of Computer Generated Forces (CGFs) is controlled through scripts. Building such scripts requires time and expertise, and becomes harder as the domain becomes richer and more life-like. These downsides can be reduced by automatically generating behavior for CGFs using machine learning techniques. This paper focuses on Dynamic Scripting (DS), a technique tailored to generating agent behavior. DS searches for an optimal combination of rules from a rule base. Under the assumption that intra-team coordination leads to more effective learning, we propose an extension of DS, called DS+C, with explicit coordination. In a comparison with regular DS we find that the addition of team coordination results in earlier convergence to optimal behavior. In addition, we achieved a performance increase of 20{\%} against an unpredictable opponent. With DS+C, behavior for CGFs can be generated that is more effective since the CGFs act on knowledge achieved by coordination and the behavior converges more efficiently than with regular DS.",
    author = "A. Toubman and Roessingh, {Jan Joris} and P.H.M. Spronck and A. Plaat and {van den Herik}, H.J.",
    year = "2014",
    language = "English",
    isbn = "9783319074542",
    volume = "8481",
    series = "Lecture Notes in Computer Science",
    publisher = "Springer International Publishing",
    pages = "440--449",
    booktitle = "Modern Advances in Applied Intelligence Lecture Notes in Computer Science",
    edition = "27",

    }

    Toubman, A, Roessingh, JJ, Spronck, PHM, Plaat, A & van den Herik, HJ 2014, Dynamic Scripting with Team Coordination in Air Combat Simulation. in Modern Advances in Applied Intelligence Lecture Notes in Computer Science: 27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2014 Proceedings, Part I. 27 edn, vol. 8481, Lecture Notes in Computer Science, Springer International Publishing, pp. 440-449 , 27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2014, Kaohsiung, Taiwan, Province of China, 3/06/14.

    Dynamic Scripting with Team Coordination in Air Combat Simulation. / Toubman, A.; Roessingh, Jan Joris; Spronck, P.H.M.; Plaat, A.; van den Herik, H.J.

    Modern Advances in Applied Intelligence Lecture Notes in Computer Science: 27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2014 Proceedings, Part I. Vol. 8481 27. ed. Springer International Publishing, 2014. p. 440-449 (Lecture Notes in Computer Science).

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

    TY - GEN

    T1 - Dynamic Scripting with Team Coordination in Air Combat Simulation

    AU - Toubman, A.

    AU - Roessingh, Jan Joris

    AU - Spronck, P.H.M.

    AU - Plaat, A.

    AU - van den Herik, H.J.

    PY - 2014

    Y1 - 2014

    N2 - Traditionally, behavior of Computer Generated Forces (CGFs) is controlled through scripts. Building such scripts requires time and expertise, and becomes harder as the domain becomes richer and more life-like. These downsides can be reduced by automatically generating behavior for CGFs using machine learning techniques. This paper focuses on Dynamic Scripting (DS), a technique tailored to generating agent behavior. DS searches for an optimal combination of rules from a rule base. Under the assumption that intra-team coordination leads to more effective learning, we propose an extension of DS, called DS+C, with explicit coordination. In a comparison with regular DS we find that the addition of team coordination results in earlier convergence to optimal behavior. In addition, we achieved a performance increase of 20% against an unpredictable opponent. With DS+C, behavior for CGFs can be generated that is more effective since the CGFs act on knowledge achieved by coordination and the behavior converges more efficiently than with regular DS.

    AB - Traditionally, behavior of Computer Generated Forces (CGFs) is controlled through scripts. Building such scripts requires time and expertise, and becomes harder as the domain becomes richer and more life-like. These downsides can be reduced by automatically generating behavior for CGFs using machine learning techniques. This paper focuses on Dynamic Scripting (DS), a technique tailored to generating agent behavior. DS searches for an optimal combination of rules from a rule base. Under the assumption that intra-team coordination leads to more effective learning, we propose an extension of DS, called DS+C, with explicit coordination. In a comparison with regular DS we find that the addition of team coordination results in earlier convergence to optimal behavior. In addition, we achieved a performance increase of 20% against an unpredictable opponent. With DS+C, behavior for CGFs can be generated that is more effective since the CGFs act on knowledge achieved by coordination and the behavior converges more efficiently than with regular DS.

    M3 - Conference contribution

    SN - 9783319074542

    VL - 8481

    T3 - Lecture Notes in Computer Science

    SP - 440

    EP - 449

    BT - Modern Advances in Applied Intelligence Lecture Notes in Computer Science

    PB - Springer International Publishing

    ER -

    Toubman A, Roessingh JJ, Spronck PHM, Plaat A, van den Herik HJ. Dynamic Scripting with Team Coordination in Air Combat Simulation. In Modern Advances in Applied Intelligence Lecture Notes in Computer Science: 27th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2014 Proceedings, Part I. 27 ed. Vol. 8481. Springer International Publishing. 2014. p. 440-449 . (Lecture Notes in Computer Science).