This study has a research object, namely data transmission lines. In this study, there are problems that must be solved related to the optimization of network transmission routes that are dynamic and adaptive to changes in real-time conditions, including latency factors, connection stability, and algorithm integration that can accommodate large-scale network needs efficiently in terms of transmission. The results obtained from this study are in the form of a model that can identify route management and optimize the border gateway protocol. The results of the study show that the application of this method can optimize the transmission path by considering network constraints and real-time condition dynamics. This study has an interpretation that the proposed model is proven to be effective in improving network performance, with increased efficiency, reduced constraints, and the ability to adapt to changes in network conditions. This is evidenced by the accuracy in the form of quantitative effectiveness by producing 95 % accuracy with the Reinforcement Learning model, able to significantly increase efficiency and accuracy compared to traditional methods in BGP routing optimization. The characteristics contained in this study include the ability to manage and identify transmission routes to improve network efficiency, reduce latency, increase throughput, minimize the number of hops in managing BGP transmission routes. There are limitations related to input data processing that require deeper annotation. This study contributes to BGP route optimization with machine learning algorithms that can be applied in complex and dynamic networks