CoopRA Algorithm for Universal Characterization of the Experimental Evaluation Results of Cooperative Multiagent Systems

Abstract

Experimental evaluation of the cooperative multiagent systems (CMASs) provides an assessment way that should be analysed. In this paper, we propose an algorithm with acronym CoopRA that can make a deep performance characterization, based on different indicators, of the experimental evaluation results of a CMAS. This could lead to the formulation of helpful information in some decisions related to the performance of the studied CMASs. In order to validate the proposed algorithm, we performed a case study on a CMAS composed of simple reactive agents that operate by mimicking the problem/task solving of natural ants. We chose this type of cooperative multiagent system architecture, based on the fact that even in case of the cooperative multiagent systems composed of simple efficiently and flexibly cooperating agents could emerges an increased problem solving intelligence at the system’s level. The evaluation was performed for the Travelling Salesman Problem (TSP) solving that is a well-known NP-hard problem, having many real-life applications.