Agent training plan for sustainable groups

Abstract

Adaptive Collaboration (AC) is to build a sustainable group that can work well even though the environment and the state of the group change. Role assignment is an important task in Role-Based Collaboration (RBC) and AC. There are many variations and different requirements in the process of role assignment. In this paper, a new requirement to build a sustainable group is established based on the analysis of the structure of a group. With this requirement, the model of RBC - E-CARGO is modified and more formal concepts are defined. A problem of agent training plan is proposed to meet this requirement and an efficient solution is proposed to solve this problem. The proposed algorithm is verified by comparisons with IBM ILOG CPLEX Optimization Platform V12.2 by randomly created groups of agents and roles. The major contribution of this paper is to clarify for the first time the problem of agent training plan for a sustainable group and proposes an efficient algorithm.