Selecting Offline Reinforcement Learning Algorithms for Stochastic Network Control

TL;DR

This paper evaluates various offline RL algorithms for stochastic wireless network control, highlighting Conservative Q-Learning's robustness and providing practical guidance for AI-driven network management.

Contribution

It offers a comprehensive evaluation of offline RL methods in stochastic telecom environments, identifying Conservative Q-Learning as the most robust approach.

Findings

Conservative Q-Learning outperforms other methods in stochastic settings.

Sequence-based methods excel with abundant high-return trajectories.

The study provides practical guidance for offline RL algorithm selection in network control.

Abstract

Offline Reinforcement Learning (RL) is a promising approach for next-generation wireless networks, where online exploration is unsafe and large amounts of operational data can be reused across the model lifecycle. However, the behavior of offline RL algorithms under genuinely stochastic dynamics -- inherent to wireless systems due to fading, noise, and traffic mobility -- remains insufficiently understood. We address this gap by evaluating Bellman-based (Conservative Q-Learning), sequence-based (Decision Transformers), and hybrid (Critic-Guided Decision Transformers) offline RL methods in an open-access stochastic telecom environment (mobile-env). Our results show that Conservative Q-Learning consistently produces more robust policies across different sources of stochasticity, making it a reliable default choice in lifecycle-driven AI management frameworks. Sequence-based methods remain competitive and can outperform Bellman-based approaches when sufficient high-return trajectories are available. These findings provide practical guidance for offline RL algorithm selection in AI-driven network control pipelines, such as O-RAN and future 6G functions, where robustness and data availability are key operational constraints.