We investigate the use of standard statistical models for quantal choice in a game theoretic setting. Players choose strategies based on relative expected utility, and assume other players do so as well. We define a Quantal Response Equilibrium (QRE) as a fixed point of this process, and establish

We describe a general model, `experience-weighted attraction' (EWA) learning, which includes reinforcement learning and a class of weighted fictitious play belief models as special cases. In EWA, strategies have attractions which reflect prior predispositions, are updated based on payoff experience, and determine choice probabilities according to some rule (e.g., logit). A key feature is a parameter delta which weights the strength of hypothetical reinforcement of strategies which were not chosen according to the payoff they would have yielded. When delta = 0 choice reinforcement results. When delta = 1, levels of reinforcement of strategies are proportional to expected payoffs given beliefs based on past history. Another key feature is the growth rates of attractions. The EWA model controls the growth rates by two decay parameters, phi and rho, which depreciate attractions and amount of experience separately. When phi = rho, belief-based models result; when rho = 0 choice reinforcement results. Using three data se...

experimental games), because it is developed for normal form games in which information about the sequential structure of a strategic situation is suppressed. In this paper we develop a theory of reciprocity for extensive games in which the sequential structure of a strategic situation is made explicit. We

of normal-form games and graphical games, and shows that these kinds of games can implement arbitrary members of a PPAD-complete class of Brouwer functions. 1

of infinite normal form games (nfgs) and the informational complexities of infinite exfgs. Known existence results, either for Nash or for correlated equilibria, only apply to a shy (non-generic) class of mcgs. Tightly controling the nitistic approximations to the information structure of mcgs delivers a

(Preliminary draft) We study the supercore of a system derived from a normal form game. For the case of a finite game, we define a sequence of games and show that the supercore coincides with the set of Nash equilibrium strategy profiles of the last game in that sequence. This result is illustrated

to predict others ’ decisions, taking their incentives into account. We study subjects ’ initial responses to normal-form games with various patterns of iterated dominance and unique pure-strategy equilibria without dominance, using a computer interface that allowed them to search for hidden payoff

We establish two links between finite-player games and their corresponding nonatomic games (NGs). In a normal-form game setting, we show that an NG’s equilibrium can generate near equilibrium payoffs for large finite games whose player types are sampled from the NG’s signature distribution

The traditional representations of games using the extensive form or the strategic (normal) form obscure much of the structure that is present in real-world games. In this paper, we propose a new representation language for general multiplayer games — multi-agent influence diagrams (MAIDs

equlibrium. In this paper we extend his result to incomplete preference using incomplete type spaces. We also show that existence of maximal element with respect to dominance relation is sufficient for order independence of iteration of strictly dominance in infinite normal form games. This extends a result