Reinforcement Learning for Deceiving Reactive Jammers in Wireless Networks

Conventional anti-jamming method mostly rely on frequency hopping to hide or escape from jammer. These approaches are not efficient in terms of bandwidth usage and can also result a high probability jamming. Different existing works, this paper, novel strategy is proposed based the idea deceiving jammer into attacking victim channel while maintaining communications legitimate users safe channels. Since jammer's information known users, an optimal selection scheme sub power allocation using reinforcement learning (RL). The performance technique evaluated by deriving statistical lower bound total received (TRP). Analytical results show that, for given access point, over 50 % highest achievable TRP, i.e. absence jammers, achieved case single user three Moreover, value increases with number available obtained compared two RL techniques, random without any jamming attacks. Simulation that outperforms methods search method, yields near TRP.