Network formation by reinforcement learning: the long and medium run

2004/04/05 by Robin Pemantle, Pemantle, Robin, Brian Skyrms +1
Computer Science · Mathematics · #60J20 #Evolutionary Algorithms and Applications #FOS: Mathematics #Probability (math.PR) #math.PR #msc:60J20

paper · pdf · doi:10.48550/arxiv.math/0404106

14 pages

arxiv created 2004/04/05 · openalex publication_date 2004/04/05 · arxiv updated 2009/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We 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.

Related

• Reinforcement learning in social networks
• A Dynamic Model of Social Network Formation
• Network and timing effects in social learning
• Learning in Repeated Interactions on Networks
• Emergence and resilience of social networks: a general theoretical framework