Reinforcement Learning (RL) is an effective way of designing model-free linear quadratic regulator (LQR) controller for linear time-invariant (LTI) networks with unknown state-space models. However, when the network size is large, conventional RL can result in unacceptably long learning time.In this paper we resolve this problem by developing an alternative approach for RL-based LQR that combines dimensionality reduction with RL theory. The approach is to construct a compressed state vector by projecting the measured state through a projective matrix. This matrix is constructed from the state measurements, and can be viewed as an empirical controllability gramian that captures the level of redundancy in the controllability of the open-loop network model. Next, a RL-controller is learned using the reduced-dimensional state instead of the original state such that the resultant cost is close to the optimal LQR cost. Numerical benefits as well as the cyber-physical implementation benefits of the proposed approach are verified using illustrative examples including an example of wide-area control of the IEEE benchmark power system.