Learning an Opponent-aware Anti-jamming Strategy via Online Convex Optimization

TL;DR

This paper introduces an online convex optimization framework with refined algorithms to improve anti-jamming strategies against intelligent jammers in radar systems, demonstrating superior performance and convergence.

Contribution

It develops novel OCO algorithms tailored for DRFM-based jammers, enhancing sample efficiency and long-term anti-jamming effectiveness.

Findings

Refined algorithms outperform standard OCO and reinforcement learning baselines.

Theoretical analysis shows improved regret bounds and long-term performance.

Simulations confirm faster convergence and better anti-jamming results.

Abstract

The dynamic competition against intelligent jammer systems presents a significant challenge to modern radar. Traditional active anti-jamming strategy learning methods often suffer from low sample efficiency and fail to fully exploit the structures of the adversary jammer. To reveal the inherent structure, this paper adopts an Online Convex Optimization (OCO) framework to capture the competition between a frequency agile radar and a digital radio frequency memory (DRFM)-based intelligent jammer. Recognizing that conventional OCO algorithms also suffer from suboptimal sample efficiency, two refined algorithms are developed that incorporate unbiased gradient estimators specifically tailored to the unique characteristics of DRFM-based jammers. Our theoretical analysis of the regret bound indicates significant improvements in long-term performance compared to standard OCO. The simulation results consistently show that our algorithms outperform traditional OCO and reinforcement learning baselines, achieving faster convergence and better anti-jamming performance.