We consider a multi-agent noncooperative game with agents’ objective functions being affected by uncertainty. Following a data driven paradigm, we represent uncertainty by means of scenarios and seek a robust Nash equilibrium solution. We treat the Nash equilibrium computation problem within the realm of probably approximately correct (PAC) learning. Building upon recent developments in scenario-based optimization, we accompany the computed Nash equilibrium with a priori and a posteriori probabilistic robustness certificates, providing confidence that the computed equilibrium remains unaffected (in probabilistic terms) when a new uncertainty realization is encountered. For a wide class of games, we also show that the computation of the so called compression set — which is at the core of scenario-based optimization — can be directly obtained as a byproduct of the proposed methodology. We demonstrate the efficacy of our approach on an electric vehicle charging control problem.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Probably approximately correct Nash equilibrium learning


    Beteiligte:
    Fele, F (Autor:in) / Margellos, K (Autor:in)

    Erscheinungsdatum :

    07.10.2020



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    DDC:    629



    Essays on Nash equilibrium refinements

    De Stefano, Federico | BASE | 2015

    Freier Zugriff

    Probably Fret?

    Anastasia Mavridou / Marie Farrell / Tom Pressburger et al. | NTRS


    Nash Equilibrium of Public Transport Service Competition

    Li, J. / Fan, B. / China Communications and Transportation Association; Transportation & Development Institute (American Society of Civil Engineers) | British Library Conference Proceedings | 2007


    Nash Equilibrium of Public Transport Service Competition

    Li, Jing / Fan, Bingquan | ASCE | 2007


    The Robust Nash equilibrium and equilibrium selection in 2x2 coordination games

    Fabella, Raul V. / Fabella, Vigile Marie B. | BASE | 2012

    Freier Zugriff