Soft Actor-Critic Deep Reinforcement Learning Based Interference Resource Allocation

Abstract

For the future information countermeasure, a single interference mode is not effective as the electromagnetic environment becomes increasingly complex. Under the condition of limited countermeasure resources, it is particularly important to formulate an appropriate interference resource allocation scheme to obtain better jamming efficacy. In this article, we model the resource allocation problem as Discrete-time Finite-state Markov Decision Process and propose a soft actor-critic deep reinforcement learning based resource allocation algorithm. With less prior information, the algorithm can learn the best allocation scheme by interacting with the environment, and avoid falling into the local optimal solution by combining with the maximization of policy information entropy. Simulation results show that the proposed algorithm is superior to the existing algorithms in stability and optimization speed.