Generalizable Multi-Task Learning for Wireless Networks Using Prompt Decision Transformers
2026-06-03 • Networking and Internet Architecture
Networking and Internet ArchitectureArtificial Intelligence
AI summaryⓘ
The authors explain that future wireless networks need smarter ways to manage how signals are shared across many cell towers to improve user experience. Traditional methods struggle to quickly adapt to changing network setups and demands. They introduce a new AI method called Prompt Decision Transformer (PromptDT), which treats the problem like understanding a sequence of events and learns from past data and specific hints about network tasks. Their approach works well across different network configurations, improves performance significantly, and can adapt to new scenarios without needing retraining. This makes managing wireless resources faster and more efficient in complex environments.
Radio Resource ManagementCoordinated Multipoint (CoMP)Deep Reinforcement LearningProximal Policy OptimizationPrompt Decision TransformerMulti-task LearningSequence ModelingQuality of ExperienceMulti-cell SelectionFew-shot Adaptation
Authors
Fatih Temiz, Shavbo Salehi, Melike Erol-Kantarci
Abstract
Future wireless networks demand rapid adaptation to highly heterogeneous environments and dynamic task configurations, necessitating a shift from conventional rule-based and optimization-driven radio resource management (RRM) toward artificial intelligence (AI)-driven RRM. AI-driven approaches can learn complex nonlinear relationships, generalize across diverse network conditions and enable real-time, scalable and autonomous decision-making. Among RRM techniques, coordinated multipoint (CoMP) transmission is pivotal for mitigating inter-cell interference and enhancing cell-edge performance, thereby improving quality of experience (QoE) in dense deployments. However, optimal multi-cell selection remains a complex combinatorial challenge as it requires jointly optimizing over many possible serving-cell combinations under dynamic traffic and channel conditions. Despite their success, conventional deep reinforcement learning (DRL) methods such as proximal policy optimization (PPO) suffer from poor sample efficiency, limited generalization, and costly retraining when state and action spaces change. To address these bottlenecks, we propose a Prompt Decision Transformer (PromptDT) based multi-task learning framework capable of learning across diverse network configurations and reformulating multi-cell selection as a sequence modeling problem. By leveraging offline trajectories and task-specific prompts, PromptDT enables scalable learning across diverse network configurations, including varying base stations and user equipment counts, and scheduler policies. Experimental results demonstrate that PromptDT improves QoE by up to 49% in multi-task settings compared to baselines, with performance scaling positively alongside model capacity. Moreover, PromptDT generalizes effectively to unseen tasks, achieving robust few-shot adaptation to new network configurations without retraining or fine-tuning.