Distributed frequency allocation based on stochastic game in cognitive radio networks
Wang Sanqiang · Journal of Liaoning Technical University · 2011
In order to achieve a distributed dynamic frequency allocation in cognitive radio network,a stochastic game framework is adopted.Cognitive links are modeled as selfish and rational agents.A new MARL algorithm,maximizing the average Q function algorithm(MAQ),is proposed in this study.With MAQ,distributed agents can realize an indirect coordination without exchanging their rewards and Q functions.Simulation results show that the learning efficiency of MAQ is close to that of centric learning method,while MAQ needs much less intercommunications.