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

TL;DR

DeRAN is a neuro-symbolic framework that converts deep reinforcement learning policies into interpretable, human-readable symbolic representations for open RAN network automation, enhancing transparency without significant performance loss.

Contribution

The paper introduces DeRAN, a novel neuro-symbolic approach that distills black-box DRL policies into symbolic forms using concept-driven abstractions and deep symbolic regression, improving interpretability in network control.

Findings

DeRAN achieves 78% and 87% of DRL rewards in two test cases.

DeRAN provides interpretable policies by design.

DeRAN is implemented on a live 5G O-RAN testbed.

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/DeRAN