Parametric Adaptive Learning

We investigate a general parametric model of adaptive learning. The model spans most of the adaptive learning procedures proposed in the literature where agents optimize given their ranking over actions, perhaps allowing for experimentation. It provides a convenient parametric framework to analyze experimental data and to compare the performance of previously proposed models. We study the asymptotic behavior of the model for different values of the three parameters. We identify several ``parameter clusters'' that result in qualitatively similar behavior. The analysis points out crucial parameter values and the important relationships between them.