Convention Emergence with Congested Resources

Norms and conventions enable coordination in populations of agents by establishing patterns of behaviour, which can emerge as agents interact with their environment and each other. Previous research on norm emergence typically considers pairwise interactions, where agents’ rewards are endogenously determined. In many real-life domains, however, individuals do not interact with one other directly, but with their environment, and the resources associated with actions are often congested. Thus, agents’ rewards are exogenously determined as a function of others’ actions and the environment. In this paper, we propose a framework to represent this setting by: (i) introducing congested actions; and (ii) adding a central authority, that is able to manipulate agents’ rewards. Agents are heterogeneous in terms of their reward functions, and learn over time, enabling norms to emerge. We illustrate the framework using transport modality choice as a simple scenario, and investigate the effect of representative initial, late and temporary manipulations on the emergent norms.