Integrating reconfigurable intelligent surfaces (RISs) in wireless communication systems holds tremendous promise for revolutionizing connectivity by offering scalability, cost-efficiency, and energy neutrality. However, navigating the complexities of dynamic environments poses significant challenges for power control in RIS-empowered wireless networks. The proposed methodology involves implementing a cooperative deep reinforcement learning (DRL) system with two interconnected networks, DRL-M and DRL-S. We called it as DRL master and slave DRL(M-S), which aims to optimize system performance and energy efficiency (EE). RL-M optimizes system performance by adjusting transmit beamforming and phase shift. The results show that increasing the transmit power (from 0 to 10 to 20 dB) leads to a proportional increase in the average reward, reaching approximately values of (2.5, 4.8, 7.8). This average reward serves as feedback for the DRL-S network, assisting it in intelligently managing power transmission to adapt to changing environmental conditions by leveraging the reward feedback from DRL-M, facilitating dynamic adjustment of power transmission based on variations in these rewards, either increasing or decreasing power transmission accordingly. This chapter contributes to advancing RIS-integrated wireless systems with enhanced power control capabilities, offering a robust solution to address the challenges of power control in RIS-enabled wireless systems operating in dynamic environments.