A Simple Learning Approach for Endogenous Network Formation

We operationalize the theory associated with an economic model of network formation and conduct experiments to de-termine the feasibility of endogenous, dynamic network for-mation in multi-agent organizations. We develop a learning-based, decentralized network formation strategy that allows the agents to make network adaptation decisions based on past performance. We compare our method with a dynamic network formation process proposed in the economics liter-ature that relies on a global computation over the entire net-work structure. Our findings demonstrate that local decisions based solely on prior experience perform as well as local de-cisions based on perfect knowledge and a global computation