Cooperating to learn: knowledge discovery through intelligent learning agents

A cooperative multi-agent learning system consists of two or more learners or learning agents that cooperate rather than compete whilst attempting to complete the task at hand. The learners have the ability to learn together thus utilising one another's strengths and alleviating individual weaknesses. The paper describes the cooperative inductive learning team (CILT) multi-agent learning system that consists of two or more machine learners which induce rules from training examples. By cooperating, the individual results of the machine learners are improved and a team knowledge-base, that contains the best team results, is created.