Using reinforcement learning and artificial evolution for the detection of group identities in complex adaptive artificial societies

Corrado Grappiolo, Julian Togelius, Georgios N. Yannakakis

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    We present a computational framework capable of inferring the existence of groups, built upon social networks of reciprocal friendship, in Complex Adaptive Artificial Societies (CAAS). Our modelling framework infers the group identities by following two steps: first, it aims to learn the ongoing levels of cooperation among the agents and, second, it applies evolutionary computation, based on the learned cooperation values, to partition the agents into groups. Experimental investigations, based on CAAS of agents who interact with each other by means of the Ultimatum Game, show that a cooperation learning phase, based on Reinforcement Learning, can provide highly promising results for minimising the mismatch between the existing and the inferred groups, for two different society sizes under investigation.

    Original languageEnglish (US)
    Title of host publicationGECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion
    Pages27-28
    Number of pages2
    DOIs
    StatePublished - 2013
    Event15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013 - Amsterdam, Netherlands
    Duration: Jul 6 2013Jul 10 2013

    Other

    Other15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013
    CountryNetherlands
    CityAmsterdam
    Period7/6/137/10/13

    Fingerprint

    Reinforcement learning
    Reinforcement Learning
    Evolutionary algorithms
    Evolutionary Computation
    Experimental Investigation
    Social Networks
    Partition
    Game
    Modeling
    Framework

    Keywords

    • Artificial societies
    • Evolutionary computation
    • Group identity detection
    • Reinforcement learning
    • Ultimatum game

    ASJC Scopus subject areas

    • Computational Mathematics

    Cite this

    Grappiolo, C., Togelius, J., & Yannakakis, G. N. (2013). Using reinforcement learning and artificial evolution for the detection of group identities in complex adaptive artificial societies. In GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion (pp. 27-28) https://doi.org/10.1145/2464576.2464589

    Using reinforcement learning and artificial evolution for the detection of group identities in complex adaptive artificial societies. / Grappiolo, Corrado; Togelius, Julian; Yannakakis, Georgios N.

    GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion. 2013. p. 27-28.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Grappiolo, C, Togelius, J & Yannakakis, GN 2013, Using reinforcement learning and artificial evolution for the detection of group identities in complex adaptive artificial societies. in GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion. pp. 27-28, 15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013, Amsterdam, Netherlands, 7/6/13. https://doi.org/10.1145/2464576.2464589
    Grappiolo C, Togelius J, Yannakakis GN. Using reinforcement learning and artificial evolution for the detection of group identities in complex adaptive artificial societies. In GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion. 2013. p. 27-28 https://doi.org/10.1145/2464576.2464589
    Grappiolo, Corrado ; Togelius, Julian ; Yannakakis, Georgios N. / Using reinforcement learning and artificial evolution for the detection of group identities in complex adaptive artificial societies. GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion. 2013. pp. 27-28
    @inproceedings{890149f37fb94559bb52ae02d2dcc3e8,
    title = "Using reinforcement learning and artificial evolution for the detection of group identities in complex adaptive artificial societies",
    abstract = "We present a computational framework capable of inferring the existence of groups, built upon social networks of reciprocal friendship, in Complex Adaptive Artificial Societies (CAAS). Our modelling framework infers the group identities by following two steps: first, it aims to learn the ongoing levels of cooperation among the agents and, second, it applies evolutionary computation, based on the learned cooperation values, to partition the agents into groups. Experimental investigations, based on CAAS of agents who interact with each other by means of the Ultimatum Game, show that a cooperation learning phase, based on Reinforcement Learning, can provide highly promising results for minimising the mismatch between the existing and the inferred groups, for two different society sizes under investigation.",
    keywords = "Artificial societies, Evolutionary computation, Group identity detection, Reinforcement learning, Ultimatum game",
    author = "Corrado Grappiolo and Julian Togelius and Yannakakis, {Georgios N.}",
    year = "2013",
    doi = "10.1145/2464576.2464589",
    language = "English (US)",
    isbn = "9781450319645",
    pages = "27--28",
    booktitle = "GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion",

    }

    TY - GEN

    T1 - Using reinforcement learning and artificial evolution for the detection of group identities in complex adaptive artificial societies

    AU - Grappiolo, Corrado

    AU - Togelius, Julian

    AU - Yannakakis, Georgios N.

    PY - 2013

    Y1 - 2013

    N2 - We present a computational framework capable of inferring the existence of groups, built upon social networks of reciprocal friendship, in Complex Adaptive Artificial Societies (CAAS). Our modelling framework infers the group identities by following two steps: first, it aims to learn the ongoing levels of cooperation among the agents and, second, it applies evolutionary computation, based on the learned cooperation values, to partition the agents into groups. Experimental investigations, based on CAAS of agents who interact with each other by means of the Ultimatum Game, show that a cooperation learning phase, based on Reinforcement Learning, can provide highly promising results for minimising the mismatch between the existing and the inferred groups, for two different society sizes under investigation.

    AB - We present a computational framework capable of inferring the existence of groups, built upon social networks of reciprocal friendship, in Complex Adaptive Artificial Societies (CAAS). Our modelling framework infers the group identities by following two steps: first, it aims to learn the ongoing levels of cooperation among the agents and, second, it applies evolutionary computation, based on the learned cooperation values, to partition the agents into groups. Experimental investigations, based on CAAS of agents who interact with each other by means of the Ultimatum Game, show that a cooperation learning phase, based on Reinforcement Learning, can provide highly promising results for minimising the mismatch between the existing and the inferred groups, for two different society sizes under investigation.

    KW - Artificial societies

    KW - Evolutionary computation

    KW - Group identity detection

    KW - Reinforcement learning

    KW - Ultimatum game

    UR - http://www.scopus.com/inward/record.url?scp=84882317793&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84882317793&partnerID=8YFLogxK

    U2 - 10.1145/2464576.2464589

    DO - 10.1145/2464576.2464589

    M3 - Conference contribution

    SN - 9781450319645

    SP - 27

    EP - 28

    BT - GECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion

    ER -