Unmanned aerial vehicle (UAV) network is vulnerable to jamming attacks, which may cause severe damage like communication outages. Due to the energy constraint, the source UAV cannot blindly enlarge the transmit power, along with the complex network topology with high mobility, which makes the destination UAV unable to evade the jammer by flying at will. To maintain communication with a limited battery capacity in the UAV networks in the presence of a greedy jammer, in this paper, we propose a distributed reinforcement learning (RL) based energy-efficient framework for the UAV networks with constrained energy under jamming attacks to improve the communication quality while minimizing the total energy consumption of the network. This framework enables each relay UAV to independently select its transmit power based on historical state-related information without knowing the moving trajectory of other UAVs as well as the jammer. The location and battery level of each UAV need not be shared with other UAVs. We also propose a deep RL based anti-jamming relay approach for UAVs with portable computation equipment like Raspberry Pi to achieve higher and faster performance. We study the Nash equilibrium (NE) and the performance bounds based on the formulated power control game. Simulation results show that the proposed schemes can reduce the bit error rate (BER) and reduce energy consumption of the UAV network compared with the benchmark method.

The video transmission in the Internet-of-Things (IoT) system must guarantee the video quality and reduce the packet loss rate and the delay with limited resources to satisfy the requirement of multimedia services. In this paper, we propose a reinforcement learning based energy-efficient IoT video transmission scheme that protects against interference, in which the base station controls the transmission action of the IoT device including the encoding rate, the modulation and coding scheme, and the transmit power. A reinforcement learning algorithm state-action-reward-state-action is applied to choose the transmission action based on the observed state (the queue length of the buffer, the channel gain, the previous bit error rate, and the previous packet loss rate) without knowledge of the transmission channel model at the transmitter and the receiver. We also propose a deep reinforcement learning based energy-efficient IoT video transmission scheme that uses a deep neural network to approximate $Q$ value to further accelerate the learning process involved in choosing the optimal transmission action and improve the video transmission performance. Moreover, both the performance bounds of the proposed schemes and the computational complexity are theoretically derived. Simulation results show that the proposed schemes can increase the peak signal-to-noise ratio and decrease the packet loss rate, the delay, and the energy consumption relative to the benchmark scheme.