Network formation by reinforcement learning: the long and medium run

Simple item page
dc.creatorPemantle, Robin
dc.creatorSkyrms, Brian
dc.date2004-04-05
dc.date.accessioned2026-07-07T05:07:10Z
dc.date.available2026-07-07T05:07:10Z
dc.descriptionWe investigate a simple stochastic model of social network formation by the process of reinforcement learning with discounting of the past. In the limit, for any value of the discounting parameter, small, stable cliques are formed. However, the time it takes to reach the limiting state in which cliques have formed is very sensitive to the discounting parameter. Depending on this value, the limiting result may or may not be a good predictor for realistic observation times.
dc.description14 pages
dc.identifierhttps://arxiv.org/abs/math/0404106
dc.identifierhttp://arxiv.org/abs/math/0404106
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/70752
dc.subjectProbability
dc.subject60J20
dc.titleNetwork formation by reinforcement learning: the long and medium run
dc.typetext

Files

Collections

arXiv