This work studies the problem of the emergence of norms in multi-agent systems. Based on a socially interactive game environment for the ”rules of the road” problem, of choosing a side of the road to drive on, a series of simulations are run in order to highlight the importance of the topology of the network underlying the multi-agent system and the influence of the population size. The simulation environment is optimized to run simulations of large multi-agent systems and the network topologies studied are: strongly regular, complete, random, random regular, small world and scale free.