Open access
Aug 2026
Federated and Communication-Efficient Decentralized Meta-Reinforcement Learning for Dynamic Spectrum Access in Cognitive Radio–Enabled 5G IoT Networks
Simulations across various 5G IoT spectrum environments showed that F-DMRL performed faster adaptation, higher spectral efficiency, and lower interference probability compared to centralized meta-RL, federated DRL, and traditional decentralized RL baselines.
Jayesh Kumar Dabi, Priyadarshi Ashok Dahat
· International Journal of Wir... · 0 citations