This paper presents a novel sim-to-real approach for training humanoid robot locomotion policies by injecting state-dependent perturbations into joint torque space during simulation. Unlike traditional domain randomization methods that randomize fixed parameters, the proposed approach uses neural networks to generate complex, state-dependent perturbations that simulate nonlinear actuator dynamics and contact compliance. The method achieves superior robustness against unseen reality gaps, demonstrating successful transfer from simulation to real-world humanoid deployment without requiring additional training. Experimental validation confirms that policies trained with this perturbation injection technique can handle complex real-world scenarios that standard randomization cannot capture.