Norm-Based Behavior Regulating Technique for Multi-Agent in Complex Adaptive Systems

Abstract

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%.

Designing Intelligent Agents in Normative Systems Toward Data Regulation Representation

“…To identify environmental norms, [43] proposes the RNDT (Regulative Norms Detection Technique), a technique to detect norms considering their rewards and penalties. Even though addressing norms challenges is not our focus, the authors proposed a norm taxonomy that classifies norms as follows: (i) regulative, (ii) constructive, and (iii) procedural.…”

A Survey of Adaptive Multi-Agent Networks and Their Applications in Smart Cities

“…It was shown that in the pattern mining of multi-agent networks, relying on occurrence frequency is sometimes misleading and new metrics such as sequence virtual growth rate are necessary to identify highly correlated patterns with a significant trend sequence in the graph [166]. Norm mining is another category that investigates events triggering rewards and penalties and identifies the norms in a varying environment setting [167]. This will help agents to survive and adapt to their environment without the deprivation of their resources and services.…”

Agent-Based Decentralized Grid Model

“…Agent technology is widely used in grid systems [13] [14]. An agent can sense the environment, take appropriate actions to establish its own code of conduct and influence environmental change, which provides an effective tool for solving network distributed application problems [15] [16] [17]. Thus, agent technology is introduced for improving the scalability, stability and efficiency of grid systems in this model.…”