The problem of unmanned aerial vehicle(UAV)power control is studied in non-cooperative envi-ronment.Considering the anti-competitive relationships between UAVs and jammers,the UAVs who act as the leader and choose power strategy and take action first,whereas the jammer acting as the follower and select jam-ming power strategy after perceiving the UAV's behavior.In addition,a Bayesian-Stackelberg game has been used to characterize behavior between UAVs and the jammers due to the incomplete information condition.A hi-erarchical Q-Learning algorithm is proposed to obtain the Stackelberg equilibrium and achieve stable convergence of UAVs power optimization solutions.Finally,the effectiveness of the proposed method is verified through ex-perimental simulations.
关键词
功率控制/Q学习/Bayesian-Stackelberg
Key words
power control/Q-learning/Bayesian-Stackelberg game
维普
万方数据