Inductive approach for QoS packet scheduling in dynamic networks

This paper deals with the problem of packet scheduling in routers. The scheduling envisaged allows to achieve QoS differentiation and to reduce the queuing delay in order to optimize the end to end delay. We model this problem as a multi-agent system which consists of a whole of autonomous and independently learning agents, where each agent learns through continual interaction with the environment in order to optimize its own behaviour while increasing the performance of the system. Coordination graphs explicitly represent where coordination between agents is required, thus preventing the agents from engaging in unnecessary coordination activities.