Development of swarm behavior in artificial learning agents that adapt to different foraging environments
Fig 10
Evolution of the global alignment parameter through the learning processes with dF = 4,21.
At each trial, there is one data point that displays the average of the order parameter, first over all the (global) interaction rounds of the trial and then over 20 different ensembles of agents, where each ensemble learns the task independently. Shaded areas represent one standard deviation.