The paper introduces a novel approach to the classical adaptive traffic signal control (TSC) problem. Instead of the traditional optimization or simple rule-based approach, Artificial Intelligence is applied. Reinforcement Learning is a spectacularly evolving realm of Machine Learning which owns the key features such as generalization, scalability, real-time applicability for solving the traffic signal control problem. Nevertheless, the researchers’ responsibilities become more serious regarding the formulation of state representation and the rewarding system. These Reinforcement Learning features are also the most fascinating and controversial virtues since the utilized abstractions decide whether the algorithm solves the problem or not. This paper proposes a new interpretation for the feature-based state representation and rewarding concept that makes the TSC problem highly generalizable and has scaling potential. The proposed method’s feasibility is demonstrated via a simulation study using a high-fidelity microscopic traffic simulator. The results justify that the Deep Reinforcement Learning based approach is a real candidate for real-time traffic light control.