To search, Click below search items.


All Published Papers Search Service


Multiagent Learning Model in Grid


QingKui Chen, Lichun Na


Vol. 6  No. 8  pp. 54-59


For improving the efficiency of resource use in dynamic network environment, the computational model base on multiagent is adopted, and an effective learning model based on the reinforcement learning and the multi-level organization learning is proposed in this paper. A series of formal definitions, such as the dynamic network grid (DNG), the computing agent, the cooperation computing team and the relations among them, were given. The rules are classified into the basic rules, the static rules and the dynamic rues. Using the generation technique of dynamic knowledge, the knowledge revision technique based on the reinforcement learning and the learning framework based on multi-level organizations of agents, the learning model was studied. The migration learning process was described in DNG. The experiment results show that this model resolves effectively the problems of optimization use of resources in DNG. It can be fit for grid computing and pervasive computing


multiagent, learning model, migration learning, grid