Is Selection Optimal for Scale-Free Small

Scale-free small world No free lunch theorem Internet The ‘no free lunch theorem ’ claims that for the set of all problems no algorithm performs better than random search and, thus, selection can be advantageous only on a limited set of problems. In this paper we investigate how the topo-logical structure of the environment infl uences algorithmic effi ciency. We study the performance of algorithms, using selective learning, reinforcement learning, and their combinations, in random, scale-free, and scale-free small world (SFSW) environments. The learning problem is to search for novel, not-yet-found infor-mation. We ran our experiments on a large news site and on its downloaded portion. Controlled experiments were performed on this downloaded portion: we modifi ed the topology, but preserved the publication time of the news. Our empirical results show that the selective learning is the most effi cient in SFSW topology. In non-small world topologies, however, the combination of the se-lective and reinforcement learning algorithms performs the best