Anti-Jamming Resource Allocation for Integrated Sensing and Communications Based on Game-Guided Reinforcement Learning

Abstract

Jamming attacks severely degrade both the sensing and communication performances, and thus this letter investigates the problem of anti-jamming resource allocation optimization in integrated sensing and communication (ISAC) systems. Our objective is to maximize the weighted sum of the communication rate and the effective sensing power while meeting both communication and sensing requirements against malicious jamming. Since the joint optimization of communication and sensing is a highly coupled problem as well as the jamming behavior is dynamic, we then propose an advanced game-guided deep reinforcement learning (DRL) algorithm to address the resource allocation issue. Specifically, the power control problem is modeled as a Markov Decision Process (MDP), while the channel selection problem is formulated as a Stackelberg game. We further prove the existence of a Stackelberg equilibrium (SE). Simulation results demonstrate that the proposed DRL-based-anti-jamming approach significantly enhances the communication and sensing performances of ISAC systems compared to other baseline methods, supporting superior resistance to inter-channel interference (ICI) and jamming attacks.