KOLEM: studies on evolution of expertise in a society of learning agents

A society of agents is one in which many agents coexist and interact with each other while carrying out their tasks. Each agent builds a certain level of expertise. Thus the interactions among agents would help each agent to carry out its task better by tapping into the collective knowledge assets of the society. Agents may differ in the ways in which they interact with other agents. As the society evolves, agents may change from one type to another. This kind of an environment presents interesting dynamics. We describe a simulator that models such a society of agents. Using a package delivery domain, agent interactions, their relative performances and the evolution and performance of the society as a whole are studied.