Generalization of Deep Reinforcement Learning for Jammer-Resilient Frequency and Power Allocation

TL;DR

This paper presents a deep reinforcement learning approach for joint frequency and power allocation that generalizes well across different wireless network scenarios and is validated through real-world over-the-air tests.

Contribution

The authors develop a training method that enhances the generalization of deep RL models for wireless resource allocation in multi-agent, jamming environments.

Findings

Improved performance on unseen network scenarios

Successful deployment on embedded software-defined radio

Validated robustness in hostile jamming conditions

Abstract

We tackle the problem of joint frequency and power allocation while emphasizing the generalization capability of a deep reinforcement learning model. Most of the existing methods solve reinforcement learning-based wireless problems for a specific pre-determined wireless network scenario. The performance of a trained agent tends to be very specific to the network and deteriorates when used in a different network operating scenario (e.g., different in size, neighborhood, and mobility, among others). We demonstrate our approach to enhance training to enable a higher generalization capability during inference of the deployed model in a distributed multi-agent setting in a hostile jamming environment. With all these, we show the improved training and inference performance of the proposed methods when tested on previously unseen simulated wireless networks of different sizes and architectures. More importantly, to prove practical impact, the end-to-end solution was implemented on the embedded software-defined radio and validated using over-the-air evaluation.