GENERAL MODEL FOR ORGANIZING INTERACTIONS IN MULTI-AGENT SYSTEMS

In this article we describe a model for finding optimal for learning the behavior of a group of agents in a collaborative multiagent setting. This model contains a set of scalable techniques that organize behavior of a multi- agent system. As a basis we use the framework of coordination graphs which exploits the dependencies between agents to decompose the global payoff function into a sum of local terms. To estimate a quality of interactions between agents we are using the concepts of the influence value learning paradigm. In last section we present the implementation of the considered model via reinforcement learning and experimental results of the use of this paradigm.