Hybrid Learning Design for Distributed Constrained Resource Optimization in 6G Networks

Abstract

Distributed Radio Resource Management (RRM) is a fundamental challenge in 6G wireless networks, particularly under dynamic user demands, multilayer inter-cell interference, and heterogeneous QoS constraints. Centralized optimization solutions are often infeasible in practice due to signaling delay and the lack of system-wide state information, while conventional multi-agent reinforcement learning (MARL) struggles with scalability and constraint satisfaction in such highly dynamic environments. We introduce a scalable two-phase hybrid learning framework to address the RRM challenges where orthogonalfrequency division multiplexing (OFDM) domain knowledge is explicitly incorporated into the MARL pipeline. We propose a scalable MARL algorithm which decomposes the original learning problem into smaller subproblems that can be handled independently, thereby avoiding exponential growth of the action space without compromising performance. Extensive simulations in realistic scenarios with 50MHz bandwidth and different numerologies show that our method significantly outperforms existing optimization and learning baselines, offering up to 30% throughput improvement, and $\mathbf{1 0 0 \%}$ constraint satisfaction with minimal resource usage.