Centralized Versus Decentralized Team Coordination Using Dynamic Scripting

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

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

    70 Downloads (Pure)

    Abstract

    Computer generated forces (CGFs) must display realistic behavior for tactical training simulations to yield an effective training experience. Tradionally, the behavior of CGFs is scripted. However, there are three drawbacks, viz. (1) scripting limits the adaptive behavior of CGFs, (2) creating scripts is difficult and
    (3) it requires scarce domain expertise. A promising machine learning technique
    is the dynamic scripting of CGF behavior. In simulating air combat scenarios, team behavior is important, both with and without communication. While dynamic scripting has been reported to be effective in creating behavior for
    single fighters, it has not often been used for team coordination. The dynamic
    scripting technique is sufficiently flexible to be used for different team coordination methods. In this paper, we report the first results on centralized
    coordination of dynamically scripted air combat teams, and compare these results to a decentralized approach from earlier work. We find that using
    the centralized approach leads to higher performance and more efficient learning, although creativity of the solutions seems bounded by the reduced complexity.
    Original languageEnglish
    Title of host publicationProceedings of the 28th European Simulation and Modelling Conference, ESM'2014
    PublisherEUROSIS
    Publication statusPublished - 2014
    Event28th European Simulation and Modelling Conference - ESM'2014' - University of Porto, Porto, Portugal
    Duration: 22 Oct 201424 Oct 2014

    Conference

    Conference28th European Simulation and Modelling Conference - ESM'2014'
    CountryPortugal
    CityPorto
    Period22/10/1424/10/14

    Fingerprint

    Air
    Learning systems
    Communication

    Cite this

    Toubman, A., Roessingh, J. J., Spronck, P. H. M., Plaat, A., & van den Herik, H. J. (2014). Centralized Versus Decentralized Team Coordination Using Dynamic Scripting. In Proceedings of the 28th European Simulation and Modelling Conference, ESM'2014 EUROSIS.
    Toubman, Armon ; Roessingh, Jan Joris ; Spronck, P.H.M. ; Plaat, Aske ; van den Herik, H.J. / Centralized Versus Decentralized Team Coordination Using Dynamic Scripting. Proceedings of the 28th European Simulation and Modelling Conference, ESM'2014. EUROSIS, 2014.
    @inproceedings{70d990fdb06247db93e5c048d2e5dc98,
    title = "Centralized Versus Decentralized Team Coordination Using Dynamic Scripting",
    abstract = "Computer generated forces (CGFs) must display realistic behavior for tactical training simulations to yield an effective training experience. Tradionally, the behavior of CGFs is scripted. However, there are three drawbacks, viz. (1) scripting limits the adaptive behavior of CGFs, (2) creating scripts is difficult and(3) it requires scarce domain expertise. A promising machine learning techniqueis the dynamic scripting of CGF behavior. In simulating air combat scenarios, team behavior is important, both with and without communication. While dynamic scripting has been reported to be effective in creating behavior forsingle fighters, it has not often been used for team coordination. The dynamicscripting technique is sufficiently flexible to be used for different team coordination methods. In this paper, we report the first results on centralizedcoordination of dynamically scripted air combat teams, and compare these results to a decentralized approach from earlier work. We find that usingthe centralized approach leads to higher performance and more efficient learning, although creativity of the solutions seems bounded by the reduced complexity.",
    author = "Armon Toubman and Roessingh, {Jan Joris} and P.H.M. Spronck and Aske Plaat and {van den Herik}, H.J.",
    year = "2014",
    language = "English",
    booktitle = "Proceedings of the 28th European Simulation and Modelling Conference, ESM'2014",
    publisher = "EUROSIS",

    }

    Toubman, A, Roessingh, JJ, Spronck, PHM, Plaat, A & van den Herik, HJ 2014, Centralized Versus Decentralized Team Coordination Using Dynamic Scripting. in Proceedings of the 28th European Simulation and Modelling Conference, ESM'2014. EUROSIS, 28th European Simulation and Modelling Conference - ESM'2014', Porto, Portugal, 22/10/14.

    Centralized Versus Decentralized Team Coordination Using Dynamic Scripting. / Toubman, Armon; Roessingh, Jan Joris; Spronck, P.H.M.; Plaat, Aske; van den Herik, H.J.

    Proceedings of the 28th European Simulation and Modelling Conference, ESM'2014. EUROSIS, 2014.

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

    TY - GEN

    T1 - Centralized Versus Decentralized Team Coordination Using Dynamic Scripting

    AU - Toubman, Armon

    AU - Roessingh, Jan Joris

    AU - Spronck, P.H.M.

    AU - Plaat, Aske

    AU - van den Herik, H.J.

    PY - 2014

    Y1 - 2014

    N2 - Computer generated forces (CGFs) must display realistic behavior for tactical training simulations to yield an effective training experience. Tradionally, the behavior of CGFs is scripted. However, there are three drawbacks, viz. (1) scripting limits the adaptive behavior of CGFs, (2) creating scripts is difficult and(3) it requires scarce domain expertise. A promising machine learning techniqueis the dynamic scripting of CGF behavior. In simulating air combat scenarios, team behavior is important, both with and without communication. While dynamic scripting has been reported to be effective in creating behavior forsingle fighters, it has not often been used for team coordination. The dynamicscripting technique is sufficiently flexible to be used for different team coordination methods. In this paper, we report the first results on centralizedcoordination of dynamically scripted air combat teams, and compare these results to a decentralized approach from earlier work. We find that usingthe centralized approach leads to higher performance and more efficient learning, although creativity of the solutions seems bounded by the reduced complexity.

    AB - Computer generated forces (CGFs) must display realistic behavior for tactical training simulations to yield an effective training experience. Tradionally, the behavior of CGFs is scripted. However, there are three drawbacks, viz. (1) scripting limits the adaptive behavior of CGFs, (2) creating scripts is difficult and(3) it requires scarce domain expertise. A promising machine learning techniqueis the dynamic scripting of CGF behavior. In simulating air combat scenarios, team behavior is important, both with and without communication. While dynamic scripting has been reported to be effective in creating behavior forsingle fighters, it has not often been used for team coordination. The dynamicscripting technique is sufficiently flexible to be used for different team coordination methods. In this paper, we report the first results on centralizedcoordination of dynamically scripted air combat teams, and compare these results to a decentralized approach from earlier work. We find that usingthe centralized approach leads to higher performance and more efficient learning, although creativity of the solutions seems bounded by the reduced complexity.

    M3 - Conference contribution

    BT - Proceedings of the 28th European Simulation and Modelling Conference, ESM'2014

    PB - EUROSIS

    ER -

    Toubman A, Roessingh JJ, Spronck PHM, Plaat A, van den Herik HJ. Centralized Versus Decentralized Team Coordination Using Dynamic Scripting. In Proceedings of the 28th European Simulation and Modelling Conference, ESM'2014. EUROSIS. 2014