We study the distribution of strategies in a large game that models how agents choose among different double auction markets. We classify the possible mean field Nash equilibria, which include potentially segregated states where an agent population can split into subpopulations adopting different strategies. As the game is aggregative, the actual equilibrium strategy distributions remain undetermined, however. We therefore compare with the results of a reinforcement learning dynamics inspired by Experience-Weighted Attraction (EWA) learning, which at long times leads to Nash equilibria in the appropriate limits of large intensity of choice, low noise (long agent memory) and perfect imputation of missing scores (fictitious play). The learning dynamics breaks the indeterminacy of the Nash equilibria. Non-trivially, depending on how the relevant limits are taken, more than one type of equilibrium can be selected. These include the standard homogeneous mixed and heterogeneous pure states, but also heterogeneous mixed states where different agents play different strategies that are not all pure. The analysis of the reinforcement learning involves Fokker-Planck modeling combined with large deviation methods. The theoretical results are confirmed by multi-agent simulations.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Dynamical selection of Nash equilibria using reinforcement learning:Emergence of heterogeneous mixed equilibria


    Beteiligte:
    Nicole, Robin (Autor:in) / Sollich, Peter (Autor:in)

    Erscheinungsdatum :

    2018-01-01


    Anmerkungen:

    Nicole , R & Sollich , P 2018 , ' Dynamical selection of Nash equilibria using reinforcement learning : Emergence of heterogeneous mixed equilibria ' , PLoS ONE , vol. 13 , no. 7 , e0196577 . https://doi.org/10.1371/journal.pone.0196577 , https://doi.org/10.1371/journal.pone.0196577



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    DDC:    629



    Target Selection for Tracking in Multifunction Radar Networks: Nash and Correlated Equilibria

    Bogdanovic, Nikola / Driessen, Hans / Yarovoy, Alexander G. | IEEE | 2018


    Nash smoothing on the test bench: Hα-essential equilibria

    Duman, Papatya / Trockel, Walter | BASE | 2020

    Freier Zugriff

    Distributed Seeking of Nash Equilibria in Mobile Sensor Networks

    Stankovic, Milos S. / Johansson, Karl H. / Stipanovic, Dusan M. | BASE | 2010

    Freier Zugriff

    Nash Smoothing on the Test Bench: $H_{\alpha}$ -Essential Equilibria

    Duman, Papatya / Trockel, Walter | BASE | 2020

    Freier Zugriff

    Interval methods for computing strong Nash equilibria of continuous games

    Kubica, Bartłomiej / Woźniak, Adam | BASE | 2016

    Freier Zugriff