In the framework of the Future Internet, the aim of the Quality of Experience (QoE) Control functionalitiesis to track the personalized desired QoE level of the applications. The paper proposes to perform such a taskby dynamically selecting the most appropriate Classes of Service (among the ones supported by the network), thisselection being driven by a novel heuristic Multi-Agent Reinforcement Learning (MARL) algorithm. The papershows that such an approach offers the opportunity to cope with some practical implementation problems: in particular,it allows to face the so-called 'curse of dimensionality' of MARL algorithms, thus achieving satisfactoryperformance results even in the presence of several hundreds of Agents.
In the framework of the Future Internet, the aim of the Quality of Experience (QoE) Control functionalitiesis to track the personalized desired QoE level of the applications. The paper proposes to perform such a taskby dynamically selecting the most appropriate Classes of Service (among the ones supported by the network), thisselection being driven by a novel heuristic Multi-Agent Reinforcement Learning (MARL) algorithm. The papershows that such an approach offers the opportunity to cope with some practical implementation problems: in particular,it allows to face the so-called 'curse of dimensionality' of MARL algorithms, thus achieving satisfactoryperformance results even in the presence of several hundreds of Agents.