Bayesian learning leads to correlated equilibria in normal form games

Yaw Nyarko

    Research output: Contribution to journalArticle

    Abstract

    Consider an infinitely repeated normal form game where each player is characterized by a "type" which may be unknown to the other players of the game. Impose only two conditions on the behavior of the players. First, impose the Savage (1954) axioms; i.e., each player has some beliefs about the evolution of the game and maximizes its expected payoffs at each date given those beliefs. Second, suppose that any event which has probability zero under one player's beliefs also has probability zero under the other player's beliefs. We show that under these two conditions limit points of beliefs and of the empirical distributions (i.e., sample path averages or histograms) are correlated equilibria of the "true" game (i.e., the game characterized by the true vector of types).

    Original languageEnglish (US)
    Pages (from-to)821-841
    Number of pages21
    JournalEconomic Theory
    Volume4
    Issue number6
    DOIs
    StatePublished - Nov 1994

    Fingerprint

    Correlated equilibrium
    Normal form games
    Bayesian learning
    Empirical distribution
    Axioms

    ASJC Scopus subject areas

    • Economics and Econometrics

    Cite this

    Bayesian learning leads to correlated equilibria in normal form games. / Nyarko, Yaw.

    In: Economic Theory, Vol. 4, No. 6, 11.1994, p. 821-841.

    Research output: Contribution to journalArticle

    Nyarko, Yaw. / Bayesian learning leads to correlated equilibria in normal form games. In: Economic Theory. 1994 ; Vol. 4, No. 6. pp. 821-841.
    @article{65536c03f85047bc99fc6550465c992d,
    title = "Bayesian learning leads to correlated equilibria in normal form games",
    abstract = "Consider an infinitely repeated normal form game where each player is characterized by a {"}type{"} which may be unknown to the other players of the game. Impose only two conditions on the behavior of the players. First, impose the Savage (1954) axioms; i.e., each player has some beliefs about the evolution of the game and maximizes its expected payoffs at each date given those beliefs. Second, suppose that any event which has probability zero under one player's beliefs also has probability zero under the other player's beliefs. We show that under these two conditions limit points of beliefs and of the empirical distributions (i.e., sample path averages or histograms) are correlated equilibria of the {"}true{"} game (i.e., the game characterized by the true vector of types).",
    author = "Yaw Nyarko",
    year = "1994",
    month = "11",
    doi = "10.1007/BF01213814",
    language = "English (US)",
    volume = "4",
    pages = "821--841",
    journal = "Economic Theory",
    issn = "0938-2259",
    publisher = "Springer New York",
    number = "6",

    }

    TY - JOUR

    T1 - Bayesian learning leads to correlated equilibria in normal form games

    AU - Nyarko, Yaw

    PY - 1994/11

    Y1 - 1994/11

    N2 - Consider an infinitely repeated normal form game where each player is characterized by a "type" which may be unknown to the other players of the game. Impose only two conditions on the behavior of the players. First, impose the Savage (1954) axioms; i.e., each player has some beliefs about the evolution of the game and maximizes its expected payoffs at each date given those beliefs. Second, suppose that any event which has probability zero under one player's beliefs also has probability zero under the other player's beliefs. We show that under these two conditions limit points of beliefs and of the empirical distributions (i.e., sample path averages or histograms) are correlated equilibria of the "true" game (i.e., the game characterized by the true vector of types).

    AB - Consider an infinitely repeated normal form game where each player is characterized by a "type" which may be unknown to the other players of the game. Impose only two conditions on the behavior of the players. First, impose the Savage (1954) axioms; i.e., each player has some beliefs about the evolution of the game and maximizes its expected payoffs at each date given those beliefs. Second, suppose that any event which has probability zero under one player's beliefs also has probability zero under the other player's beliefs. We show that under these two conditions limit points of beliefs and of the empirical distributions (i.e., sample path averages or histograms) are correlated equilibria of the "true" game (i.e., the game characterized by the true vector of types).

    UR - http://www.scopus.com/inward/record.url?scp=0000481276&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0000481276&partnerID=8YFLogxK

    U2 - 10.1007/BF01213814

    DO - 10.1007/BF01213814

    M3 - Article

    VL - 4

    SP - 821

    EP - 841

    JO - Economic Theory

    JF - Economic Theory

    SN - 0938-2259

    IS - 6

    ER -