We consider a radio resource management (RRM) problem in a multi-user wireless network, where the goal is to optimize a network-wide utility function subject to constraints on the ergodic average performance of users. We propose a state-augmented parameterization for the RRM policy, where alongside the instantaneous network states, the RRM policy takes as input the set of dual variables corresponding to the constraints. We provide theoretical justification for the feasibility and near-optimality of the RRM decisions generated by the proposed state-augmented algorithm. Focusing on the power allocation problem with RRM policies parameterized by a graph neural network (GNN) and dual variables sampled from the dual descent dynamics, we numerically demonstrate that the proposed approach achieves a superior trade-off between mean, minimum, and 5th percentile rates than baseline methods.