Multi-Agent Collaboration Planning in Mentorship Mode

In order to solve the problem of the task collaboration of multi-agent, we propose a task collaboration planning based on mentorship mode (MM-TCP). In this paper, the Group Role Assignment (GRA) framework is used to formalize the multi-agent task collaboration problem. The Growth curve is adopted to describe the change trend of the qualification values of the prior and posterior agents in a mentorship mode. The IBM ILOG CPLEX optimization package (CPLEX) is used to find the solution of the model. Experiments show that the proposed method is feasible and effective. With the utilization of a mentorship mode, the performance of the whole team is improved. In addition, the effect of the Growth curve model on team performance is also discussed in this paper.