We consider the situation in which individuals in a finite population must repeatedly choose an action yielding an uncertain payoff. Between choices, each individual may observe the performance of one other individual. We search for rules of behavior with limited memory that increase expected...

We analyze the evolution of behavioral rules for learning how to play a two-armed bandit. Individuals have no information about the underlying pay-off distributions and have limited memory about their own past experience. Instead they must rely on information obtained trough observing the...

The evolutionary selection of outcomes (modelled using the replicator dynamics) in games with costless communication depends crucially on the structural assumptions made on the underlying population. (1) In conflicts between two interacting populations, common interest implies that the set of...

In consectutive rounds, each agent in a finite population chooses an action, is randomly matched, obtains a payoff and then observes the performance of another agent. An agent determines future behavior based on the information she receives from the present round. She chooses among the...

We extend the notions of evolutionary stability and, for the first time, that of neutral stability to asymmetric games played between two populations. Stability with respect to simultaneous entry of a small proportion of mutants into both populations is considered. Allocations where neither...

Consider a large population of individuals that are repeatedly randomly matched to play a cyclic 2x2 game such as Matching Pennies with fixed roles assigned in the game. Some learn by sampling previous play of a finite number of other individuals in the same role. We analyze population dynamics...

In a recent paper Bagwell (1995) pointed out that only the Cournot outcome, but not the Stackelberg outcome, can be supported by a pure Nash equilibrium when actions of the Stackelberg leader are observed with the slightest error. The Stackelberg outcome, however, remains close to the outcome of...

We call a set of strategies "uniformly evolutionary stable" if the following holds after a small mutation of a monomorphic population playing a strategy in the set: a) No mutant strategy can spread. b) Mutant strategies not in the set will be driven out. c) The meaning of a "small mutation" can...

We consider the model of social learning by Schlag (1996). Individuals must repeatedly choose an action in a multi-armed bandit. We assume that each indivdiual observes the outcomes of two other individuals' choices before her own next choice must be made -- the original model only allows for...

A partnership game is a two person game in which both players necessarily receive the same payoff. For symmetric partnership games it is shown that asymptotic stability with respect to the replicator dynamics, evolutionary stability (Maynard Smith and Price [1973], Thomas [1985]) and equilibrium...