Decentralized learning cuts wireless collisions in shared networks
Mission-critical spectrum sharing with decentralized Multi-Agent Reinforcement Learning
Information Theory
Summary
Wireless networks often get crowded, and this causes devices to interfere and fail to send messages properly. The authors developed a way for many devices to learn on their own when to transmit so they avoid interfering with important main users and each other. Their approach uses simple learning rules that work well on small devices often found at the edge of networks. Experiments show this method cuts interruptions by almost 97% compared to random or simpler strategies. This helps keep data flowing smoothly even in busy wireless environments.
What this means in practice
- •For wireless network engineers: Deploy distributed learning algorithms on edge devices to manage spectrum use dynamically and reduce interference with critical users.
- •For telecommunications infrastructure teams: Improve throughput and reliability of spectrum access in congested areas by implementing decentralized coordination among devices.
Authors
Dimitrios Pylorof, Imtiaz Nasim, Humberto E. Garcia, Vivek Agarwal, Jasni A. Mannil, Mingyue Ji
Abstract
Motivated by emerging mission-critical applications and an increasingly congested spectrum, we develop a decentralized multi-agent reinforcement learning (MARL) model for dynamic spectrum access. The model enables secondary users to learn effective transmission strategies across shared frequency bands while minimizing collisions with high-priority primary users and among themselves. We design the agent-level learners following a Markov potential game approach, connecting independent local updates to system-level improvement. We instantiate this design using lightweight linear actor-critic learners suitable for resource-constrained edge devices, rather than computationally intensive centralized or deep multi-agent architectures. Across spectrum environments with different incumbent activities, the learned policies adapt their transmission policy and waiting behavior to preserve throughput while greatly reducing transmission collisions relative to random and forecast-aware heuristic baselines. The results establish the value of decentralized MARL and shows up to 96.8% reduction in overall collisions.