Asynchronous MultiAgent Reinforcement Learning for 5G Routing under Side Constraints
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912863624364032 |
|---|---|
| author | Racedo, Sebastian Jaumard, Brigitte Delgado, Oscar Masoudi, Meysam |
| author_facet | Racedo, Sebastian Jaumard, Brigitte Delgado, Oscar Masoudi, Meysam |
| contents | Networks in the current 5G and beyond systems increasingly carry heterogeneous traffic with diverse quality-of-service constraints, making real-time routing decisions both complex and time-critical. A common approach, such as a heuristic with human intervention or training a single centralized RL policy or synchronizing updates across multiple learners, struggles with scalability and straggler effects. We address this by proposing an asynchronous multi-agent reinforcement learning (AMARL) framework in which independent PPO agents, one per service, plan routes in parallel and commit resource deltas to a shared global resource environment. This coordination by state preserves feasibility across services and enables specialization for service-specific objectives. We evaluate the method on an O-RAN like network simulation using nearly real-time traffic data from the city of Montreal. We compared against a single-agent PPO baseline. AMARL achieves a similar Grade of Service (acceptance rate) (GoS) and end-to-end latency, with reduced training wall-clock time and improved robustness to demand shifts. These results suggest that asynchronous, service-specialized agents provide a scalable and practical approach to distributed routing, with applicability extending beyond the O-RAN domain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00035 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Asynchronous MultiAgent Reinforcement Learning for 5G Routing under Side Constraints Racedo, Sebastian Jaumard, Brigitte Delgado, Oscar Masoudi, Meysam Networking and Internet Architecture Distributed, Parallel, and Cluster Computing Machine Learning Multiagent Systems Networks in the current 5G and beyond systems increasingly carry heterogeneous traffic with diverse quality-of-service constraints, making real-time routing decisions both complex and time-critical. A common approach, such as a heuristic with human intervention or training a single centralized RL policy or synchronizing updates across multiple learners, struggles with scalability and straggler effects. We address this by proposing an asynchronous multi-agent reinforcement learning (AMARL) framework in which independent PPO agents, one per service, plan routes in parallel and commit resource deltas to a shared global resource environment. This coordination by state preserves feasibility across services and enables specialization for service-specific objectives. We evaluate the method on an O-RAN like network simulation using nearly real-time traffic data from the city of Montreal. We compared against a single-agent PPO baseline. AMARL achieves a similar Grade of Service (acceptance rate) (GoS) and end-to-end latency, with reduced training wall-clock time and improved robustness to demand shifts. These results suggest that asynchronous, service-specialized agents provide a scalable and practical approach to distributed routing, with applicability extending beyond the O-RAN domain. |
| title | Asynchronous MultiAgent Reinforcement Learning for 5G Routing under Side Constraints |
| topic | Networking and Internet Architecture Distributed, Parallel, and Cluster Computing Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2602.00035 |