Generalization In Reinforcement Learning For Radio Access Networks

Abstract

Modern RAN operate in highly dynamic and heterogeneous environments, where hand-tuned, rule-based RRM algorithms often underperform. While RL can surpass such heuristics in constrained settings, the diversity of deployments and unpredictable radio conditions introduce major generalization challenges. Data-driven policies frequently overfit to training conditions, degrading performance in unseen scenarios. To address this, we propose a generalization-centered RL framework for RAN control that: (i) robustly reconstructs dynamically varying states from partial and noisy observations, while encoding static and semi-static information, such as radio nodes, cell attributes, and their topology, through graph representations; (ii) applies domain randomization to broaden the training distribution; and (iii) distributes data generation across multiple actors while centralizing training in a cloud-compatible architecture aligned with O-RAN principles. Although generalization increases computation

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydemirel2025generalization

Related papers

• Practical Policy Distillation For Reinforcement Learning In Radio Access Networks (2025)0.00
• Anomaly Detection For Scalable Task Grouping In Reinforcement Learning-based RAN Optimization (2023)0.00
• FORLORN: A Framework For Comparing Offline Methods And Reinforcement Learning For Optimization Of RAN Parameters (2022)0.00
• Koopman-based Generalization Of Deep Reinforcement Learning With Application To Wireless Communications (2025)0.00
• Sim2real For Reinforcement Learning Driven Next Generation Networks (2022)0.00
• Offline And Distributional Reinforcement Learning For Radio Resource Management (2024)0.00
• Generalization Of Deep Reinforcement Learning For Jammer-resilient Frequency And Power Allocation (2023)0.00
• Average Reward Reinforcement Learning For Wireless Radio Resource Management (2025)2.26