Learning in network contexts: Experimental results from simulations

This paper describes the results of simulation experiments performed on a s uits of learning algorithms. We focus on games in network contexts. These a re contexts in which (1) agents have very limited information about the gam e and (2) play can be extremely asynchronous. There are many proposed learn ing algorithms in the literature. We choose a small sampling of such algori thms and use numerical simulation to explore the nature of asymptotic play. In particular, we explore the extent to which the asymptotic play depends on three factors: limited information, asynchronous play, and the degree of responsiveness of the learning algorithm. (C) 2001 Academic Press.