Article · Technologies · July 30, 2026
Robust Offline Multi-Agent Reinforcement Learning for Latency-Aware SDN Path Control in 6G-Oriented Network Softwarization
Abzal E. Kyzyrkanov, Yedil S. Nurakhov, Zhenis Otarbay, Danil V. Lebedev
Abstract
Future sixth-generation (6G)-oriented networks require programmable control that can adapt routing to latency and congestion without unsafe online exploration. This study evaluates offline multi-agent deep deterministic policy gradient (MADDPG) with behavior-adjusted training rewards for latency-aware path control in software-defined networking (SDN). Each traffic pair is modeled as an agent selecting one of three retained candidate paths, while centralized critics learn coordinated decisions from topology-specific Ryu–Mininet transition datasets. Nine policies are compared using ten paired seeds on fat-tree, mesh-grid, and WAN-corridors topologies under a deployed utilization–latency weighting of 0.60/0.40, together with flow-completion, latency, congestion, architectural-comparison, sensitivity, robustness, statistical, and controller-overhead analyses. The utilization-aware path heuristic achieves the strongest overall reward ranking. MADDPG is the strongest learned policy on fat-tree, is not significantly outperformed by any evaluated policy on mesh-grid, and remains statistically tied with completion-matched policies on WAN-corridors. Behavior adjustment is topology-dependent rather than uniformly beneficial. The exported policy requires approximately 52μs per joint decision, whereas complete control-loop timing is dominated by network-statistics polling. These results support offline multi-agent SDN control as a competitive, low-overhead option when interpreted jointly with topology structure, flow completion, and strong heuristic baselines.
More by Zhenis Otarbay
- Ocular-correlated signals and decision rules in DTW decoding of motor-imagery EEG: code and resultsZenodo · 2026
- When Deployment Changes a Learned Action: Post-Inference Projection in Offline Multi-Agent Reinforcement LearningAI · 2026
- An Exploratory Study of Gender Effects on Pupillary Cognitive Load in Human–Robot InteractionIEEE International Conference on Smart Information Systems and Technologies · 2026
- CSP-LDA Decoding of Left-Right Hand Motor Imagery EEG: Interpretable Spatial Patterns and Subject-Level Error TrendsIEEE International Conference on Smart Information Systems and Technologies · 2026