Spectrum-Agile Cognitive Interference Avoidance Through Deep Reinforcement Learning

Survey on cognitive anti‐jamming communications

“…The authors in [52] introduced a Markov jammer that follows a Markov chain for selecting which channel to jam. This type of jammer is a good candidate when fixed or completely random jamming strategies are not preferable.…”

“…The conventional RL has certain limitations when dealing with anti‐jamming systems with a large state‐action space. To tackle these challenges, some recent work has proposed using deep reinforcement learning (DRL) [52, 53, 95–100] as shown in Table 4. The DRL is a branch of DL where it uses deep artificial neural networks to enhance the learning operation of the traditional RL.…”

“…A cognitive approach for anti‐jamming and interference avoidance is discussed in [52] that can be used in partially‐observable spectrum applications. The proposed scheme uses DDQN with a CNN.…”

“…The proposed scheme uses DDQN with a CNN. The system model in [52] assumes a transmitter and a receiver operating in a heterogeneous spectrum congested with jamming and interference signals. Assuming that the receiver has cognitive capabilities (e.g.…”

“…The sensing matrix along with the chosen communications channel index and an indication whether the communications process was successful or not form the state of the underlying problem. The same problem formulation in [52] is considered in [100], but with new operation parameters and state definitions. These modifications reduce the computational complexity and improve the performance compared to that of [52].…”