LAUSR

In a complex adaptive system, norms are widely used to regulate agents’ behavior within a society in which the agents are not explicitly given the norms of different host systems, but instead detect and adapt the norms autonomously. Thus, failing to adopt a host’s norms resulting in deprived of accessing resources and services that would severely affect their performance. Few attempts have been made to overcome this problem but proposed solutions lack accuracy in identifying the norms of a domain. Consequently, this paper demonstrates a new effective technique called Regulative Norms Detection Technique (RNDT) to detect norms by analyzing odd events that trigger reward or penalty. Several tests have been conducted on agents exploiting the technique to detect norms in a virtual domain under varying environmental settings. The tests’ results show that the RNDT achieve well although the rate of success relies on the environmental variables settings. Specifically, the result shows that the rate of adopting the domain’s norms using RNDT is 78.0%. The rate of rewarded agents in three testing cycles increased from 30% to 70%, the rate of neutral agents also increased from 35% to 45%. The most noticeable change is in the penalty case in which 35% of agents are penalized in cycle 1, while in cycle 2 and 3 the rate is maintained at 0.0%.