Evolving models of player decision making

Personas versus clones

Christoffer Holmgård, Antonios Liapis, Julian Togelius, Georgios N. Yannakakis

    Research output: Contribution to journalArticle

    Abstract

    The current paper investigates multiple approaches to modeling human decision making styles for procedural play-testing. Building on decision and persona theory we evolve game playing agents representing human decision making styles. Three kinds of agents are evolved from the same representation: procedural personas, evolved from game designer expert knowledge, clones, evolved from observations of human play and aimed at general behavioral replication, and specialized agents, also evolved from observation, but aimed at determining the maximal behavioral replication ability of the representation. These three methods are then compared on their ability to represent individual human decision makers. Comparisons are conducted using three different proposed metrics that address the problem of matching decisions at the action, tactical, and strategic levels. Results indicate that a small gallery of personas evolved from designer intuitions can capture human decision making styles equally well as clones evolved from human play-traces for the testbed game MiniDungeons.

    Original languageEnglish (US)
    Pages (from-to)95-104
    Number of pages10
    JournalEntertainment Computing
    Volume16
    DOIs
    StatePublished - Jul 1 2016

    Fingerprint

    Decision making
    Testbeds
    Testing

    Keywords

    • Decision making
    • Evolutionary computation
    • Player modeling
    • Procedural content generation

    ASJC Scopus subject areas

    • Human-Computer Interaction
    • Software

    Cite this

    Evolving models of player decision making : Personas versus clones. / Holmgård, Christoffer; Liapis, Antonios; Togelius, Julian; Yannakakis, Georgios N.

    In: Entertainment Computing, Vol. 16, 01.07.2016, p. 95-104.

    Research output: Contribution to journalArticle

    Holmgård, Christoffer ; Liapis, Antonios ; Togelius, Julian ; Yannakakis, Georgios N. / Evolving models of player decision making : Personas versus clones. In: Entertainment Computing. 2016 ; Vol. 16. pp. 95-104.
    @article{01a66d62d67c455a93134b97c0e6d87d,
    title = "Evolving models of player decision making: Personas versus clones",
    abstract = "The current paper investigates multiple approaches to modeling human decision making styles for procedural play-testing. Building on decision and persona theory we evolve game playing agents representing human decision making styles. Three kinds of agents are evolved from the same representation: procedural personas, evolved from game designer expert knowledge, clones, evolved from observations of human play and aimed at general behavioral replication, and specialized agents, also evolved from observation, but aimed at determining the maximal behavioral replication ability of the representation. These three methods are then compared on their ability to represent individual human decision makers. Comparisons are conducted using three different proposed metrics that address the problem of matching decisions at the action, tactical, and strategic levels. Results indicate that a small gallery of personas evolved from designer intuitions can capture human decision making styles equally well as clones evolved from human play-traces for the testbed game MiniDungeons.",
    keywords = "Decision making, Evolutionary computation, Player modeling, Procedural content generation",
    author = "Christoffer Holmg{\aa}rd and Antonios Liapis and Julian Togelius and Yannakakis, {Georgios N.}",
    year = "2016",
    month = "7",
    day = "1",
    doi = "10.1016/j.entcom.2015.09.002",
    language = "English (US)",
    volume = "16",
    pages = "95--104",
    journal = "Entertainment Computing",
    issn = "1875-9521",
    publisher = "Elsevier",

    }

    TY - JOUR

    T1 - Evolving models of player decision making

    T2 - Personas versus clones

    AU - Holmgård, Christoffer

    AU - Liapis, Antonios

    AU - Togelius, Julian

    AU - Yannakakis, Georgios N.

    PY - 2016/7/1

    Y1 - 2016/7/1

    N2 - The current paper investigates multiple approaches to modeling human decision making styles for procedural play-testing. Building on decision and persona theory we evolve game playing agents representing human decision making styles. Three kinds of agents are evolved from the same representation: procedural personas, evolved from game designer expert knowledge, clones, evolved from observations of human play and aimed at general behavioral replication, and specialized agents, also evolved from observation, but aimed at determining the maximal behavioral replication ability of the representation. These three methods are then compared on their ability to represent individual human decision makers. Comparisons are conducted using three different proposed metrics that address the problem of matching decisions at the action, tactical, and strategic levels. Results indicate that a small gallery of personas evolved from designer intuitions can capture human decision making styles equally well as clones evolved from human play-traces for the testbed game MiniDungeons.

    AB - The current paper investigates multiple approaches to modeling human decision making styles for procedural play-testing. Building on decision and persona theory we evolve game playing agents representing human decision making styles. Three kinds of agents are evolved from the same representation: procedural personas, evolved from game designer expert knowledge, clones, evolved from observations of human play and aimed at general behavioral replication, and specialized agents, also evolved from observation, but aimed at determining the maximal behavioral replication ability of the representation. These three methods are then compared on their ability to represent individual human decision makers. Comparisons are conducted using three different proposed metrics that address the problem of matching decisions at the action, tactical, and strategic levels. Results indicate that a small gallery of personas evolved from designer intuitions can capture human decision making styles equally well as clones evolved from human play-traces for the testbed game MiniDungeons.

    KW - Decision making

    KW - Evolutionary computation

    KW - Player modeling

    KW - Procedural content generation

    UR - http://www.scopus.com/inward/record.url?scp=84977571624&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84977571624&partnerID=8YFLogxK

    U2 - 10.1016/j.entcom.2015.09.002

    DO - 10.1016/j.entcom.2015.09.002

    M3 - Article

    VL - 16

    SP - 95

    EP - 104

    JO - Entertainment Computing

    JF - Entertainment Computing

    SN - 1875-9521

    ER -