Generalization of Deep Reinforcement Learning for Jammer-Resilient Frequency and Power Allocation
This addresses the problem of jammer-resilient resource allocation for wireless networks, but it is incremental as it builds on existing deep reinforcement learning methods to enhance generalization.
The paper tackles the problem of joint frequency and power allocation in wireless networks to improve generalization of deep reinforcement learning models across different network scenarios, showing improved training and inference performance on unseen simulated networks and validating the solution with over-the-air evaluation on embedded software-defined radio.
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.