Interaction-based group identity detection via reinforcement learning and artificial evolution

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 group identities, built upon social networks of reciprocal friendship, in Complex Adaptive Artificial So- cieties (CAAS) by solely observing the flow of interactions occurring among the agents. Our modelling framework in- fers 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 and assign group identities to the agents. Experimental investigations, based on CAAS of agents who interact with each other by means of the Ultimatum (or Bargain) Social Dilemma Game, show that a cooperation learning phase, based on Reinforcement Learning, can pro- vide highly promising results for minimising the mismatch between the existing and the inferred group identities. The proposed method appears to be robust independently of the size and the ongoing social dynamics of the societies.

    Original languageEnglish (US)
    Title of host publicationGECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion
    Pages1423-1430
    Number of pages8
    DOIs
    StatePublished - 2013
    Event15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013 - Amsterdam, Netherlands
    Duration: Jul 6 2013Jul 10 2013

    Publication series

    NameGECCO 2013 - Proceedings of the 2013 Genetic and Evolutionary Computation Conference Companion

    Other

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

    Keywords

    • Adaptive artificial societies
    • Evolutionary com- putation
    • Group identity detection
    • Reinforcement learning
    • Ul- timatum game

    ASJC Scopus subject areas

    • Computational Mathematics

    Fingerprint

    Dive into the research topics of 'Interaction-based group identity detection via reinforcement learning and artificial evolution'. Together they form a unique fingerprint.

    Cite this