Mobile edge computing (MEC) plays a significant role in the Internet of Things (IoT)-based systems, where the nodes compute the tasks assisted by the nearby nodes instead of the remote cloud, thus reducing the latency and energy consumption substantially. The main intends of MEC is to reduce the latency and to support location awareness in order to increase the capacity of the applications that run on mobile devices. Mobile Edge Computing networks for intelligent internet of things, where multiple users have some computational tasks assisted by multiple computational access points (CAPs).
   By offloading some tasks to the CAPs, the system performance improves by reducing the latency and energy consumption, which are the two important metrics of interest in the MEC networks. An effective way of proposing the offloading strategy intelligently through the deep reinforcement learning algorithm, Deep Q- network automatically learn the offloading decision in order to optimize the system performance, and a neural network (NN) is trained to predict the offloading action, where the training data is generated from the environmental system.