Explainable AI for Radar Resource Management: Modified LIME in Deep Reinforcement Learning

TL;DR

This paper introduces DL-LIME, an improved explainability method for deep reinforcement learning in radar resource management, enhancing interpretability and performance over traditional LIME.

Contribution

The paper proposes DL-LIME, a modified LIME that incorporates deep learning into the sampling process, improving explanations and decision-making insights in radar resource management.

Findings

DL-LIME outperforms conventional LIME in fidelity and task performance.

DL-LIME provides better insights into decision factors.

Numerical results confirm improved interpretability and effectiveness.

Abstract

Deep reinforcement learning has been extensively studied in decision-making processes and has demonstrated superior performance over conventional approaches in various fields, including radar resource management (RRM). However, a notable limitation of neural networks is their ``black box" nature and recent research work has increasingly focused on explainable AI (XAI) techniques to describe the rationale behind neural network decisions. One promising XAI method is local interpretable model-agnostic explanations (LIME). However, the sampling process in LIME ignores the correlations between features. In this paper, we propose a modified LIME approach that integrates deep learning (DL) into the sampling process, which we refer to as DL-LIME. We employ DL-LIME within deep reinforcement learning for radar resource management. Numerical results show that DL-LIME outperforms conventional LIME in terms of both fidelity and task performance, demonstrating superior performance with both metrics. DL-LIME also provides insights on which factors are more important in decision making for radar resource management.