This work proposes a novel and scalable reinforcement learning approach for routing in ad-hoc wireless networks. In most previous reinforcement learning based routing methods, the links in the network are assumed to be fixed, and a different agent is trained for
each transmission node — this limits scalability and generalizability. In this paper, we account for the inherent signal-to-interference-plus-noise ratio (SINR) in the physical layer and propose a more scalable approach in which a single agent is associated with each flow and is trained using a novel reward definition and according to the physical-layer characteristics of the environment. This allows a
highly effective routing strategy based on the geographic locations of the nodes in the ad-hoc network. The proposed deep reinforcement learning strategy is capable of accounting for the mutual interference between the links and is capable of producing highly effective routing solutions over the entire network in a scalable manner.