A regulative norms mining algorithm for complex adaptive system

Abstract

In complex adaptive system, a visitor agent is not usually and explicitly given the norms of its host agent. Thus, when it is not able to adapt the host agent’s norms, it is totally deprived of accessing resources and services from the host. Such circumstance severely affects its performance resulting in failure to achieve its goal. Consequently, this paper attempts to resolve the problem by enabling the agent to identify the host’s regulative norms via an algorithm called the Regulative Norms Mining Algorithm (RNMA). Regulative norms constitute the recommendation, obligation, and prohibition norms, which the RNMA identifies by analyzing exceptional events that trigger rewards or penalties. In this paper, we argue that existing norms identifications algorithms are inadequate to detect different regulative norm types. Consequently, we propose the RNMA algorithm, which could alleviate the problem. We demonstrate the merit of the algorithm by apply it on a typical scenario. © 2018, Springer International Publishing AG.