%0 Journal Article
%T Norm Emergence in Multi-Agent Systems Based on Social Interactions
%A Marius-Tudor BENEA
%A Teodor Andrei T£¿RT£¿REANU
%A Mihai TR£¿SC£¿U
%J Computer Science Master Research
%D 2011
%I 
%X Norms establish many aspects of human behavior. While most of them are considered to be optional, some are used to create laws that govern our lives. In multi-agent systems (MAS), norms are very useful in establishing and sustaining a social order for the general behavior of the agents, while increasing cooperation and coordination, and reducing computational efforts by shifting from a centralized, top-down architecture, to an agent-based, bottom-up design. This paper presents several norm spreading and emergence mechanisms implemented and tested with a socially interactive game environment to demonstrate their capabilities. Also, normative strategy and underlying social network topology influences are studied in a series of experiments.
%K norm
%K emergence
%K MAS
%K Q-learning
%K topology
%K social interaction
%U http://csmr.cs.pub.ro/index.php/csmr/article/view/33