Demystifying Deep Reinforcement Learning: A Neuro-Symbolic Framework for Interpretable Open RAN Automation

2026-05-11

AI Summary

This work addresses the challenge of deploying deep reinforcement learning (DRL) in Open Radio Access Networks (O-RAN), where its black-box nature and stochastic behavior hinder operator trust and safe adoption in carrier-grade networks. To overcome this, the authors propose DeRAN, a novel framework that integrates a concept-driven abstraction layer with a symbolic policy synthesis mechanism. DeRAN transforms high-dimensional telemetry data into semantic features and employs Deep Symbolic Regression (DSR) for continuous control tasks and Neural-guided Differentiable Logic (NUDGE) for discrete ones, yielding human-readable symbolic policies. Evaluated on a real-world 5G O-RAN platform, DeRAN achieves 78% and 87% of the cumulative reward attained by the original DRL agent in two representative use cases, while providing inherent interpretability and auditability.

Abstract

Open Radio Access Networks (O-RAN) are increasingly adopting data-driven control through Deep Reinforcement Learning (DRL) to optimize complex tasks such as network slicing and mobility management. However, the deployment of DRL in carrier-grade networks is hindered by its inherent opacity and stochastic execution, which limit operator trust, auditability, and safe deployment. Existing explainable AI (XAI) approaches primarily provide post-hoc insights and fail to produce executable, interpretable policies suitable for operational environments. In this paper, we present DeRAN, a neuro-symbolic framework that bridges the gap between DRL performance and operational transparency by distilling black-box DRL policies into human-readable symbolic representations. DeRAN introduces a concept-driven abstraction layer that transforms high-dimensional network telemetry into a compact set of semantically meaningful features, enabling interpretable policy learning. Building on the semantically grounded concepts, DeRAN synthesizes symbolic policies using deep symbolic regression (DSR) for continuous control and neurally guided differentiable logic (NUDGE) for discrete decision-making. We implement DeRAN on a live 5G O-RAN testbed and evaluate it on two representative use cases. Experimental results demonstrate that DeRAN achieves 78\% and 87\% of DRL's cumulative rewards in the two use cases, while offering interpretability and auditability by design. Source code is available at https://github.com/Jadejavu/A-Neuro-Symbolic-Framework-for-Interpretable-Open-RAN-Automation

Problem

• Deep Reinforcement Learning
• Open RAN
• Interpretability
• Explainable AI
• Policy Transparency

Innovation

• Neuro-Symbolic AI
• Deep Reinforcement Learning
• Interpretable Policy
• Open RAN Automation
• Symbolic Regression