Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/146964 
Autor:innen: 
Erscheinungsjahr: 
2015
Schriftenreihe/Nr.: 
Working Paper No. 15-1
Verlag: 
University of California, Department of Economics, Davis, CA
Zusammenfassung: 
It is known that there are uncoupled learning heuristics leading to Nash equilibrium in all finite games. Why should players use such learning heuristics and where could they come from? We show that there is no uncoupled learning heuristic leading to Nash equilibrium in all finite games that a player has an incentive to adopt, that would be "evolutionary stable" or that "could learn itself". Rather, a player has an incentive to strategically teach such a learning opponent in order secure at least the Stackelberg leader payoff. The impossibility result remains intact when restricted to the classes of generic games, two-player games, potential games, games with strategic complements or 2x2 games, in which learning is known to be "nice". More generally, it also applies to uncoupled learning heuristics leading to correlated equilibria, rationalizable outcomes, iterated admissible outcomes, or minimal curb sets. A possibility result restricted to "strategically trivial" games fails if some generic games outside this class are considered as well.
Schlagwörter: 
learning in games
learning heuristics
learning rules
interactive learning
uncoupled learning
meta-learning
Nash equilibrium
correlated equilibrium
rationalizability
iterated admissibility
minimal curb sets
dominance solvable games
common interest games
reputation
JEL: 
C72
C73
Dokumentart: 
Working Paper

Datei(en):
Datei
Größe
927.58 kB





Publikationen in EconStor sind urheberrechtlich geschützt.