In February 2025, Ahmed Elgallad developed a new Critic network architecture for the WE-Autopilot/Red-Team repository, targeting the f1tenth_gym reinforcement learning environment. He designed a CNN-based state processing pipeline combined with fully connected layers to enhance state-action value estimation, aiming to improve policy evaluation stability. Ahmed implemented the solution in Python using PyTorch, integrating the Adam optimizer with configurable learning rates and robust checkpointing to ensure reproducible training and smoother convergence. This work addressed the need for more reliable policy updates and faster experimentation in autonomous driving simulations, demonstrating depth in deep learning and reinforcement learning engineering within a production codebase.