In this innovative approach, we leverage Reinforcement Learning alongside Deep Q-Networks and Genetic Algorithms to autonomously optimize designs. RL, through its iterative learning process, guides the agent to explore and exploit potential modifications to the design. DQN enhances the learning process by approximating the optimal action-value function, enabling efficient decision-making in complex environments. Genetic Algorithms complement RL by providing an evolutionary approach to exploring diverse designs and exploiting favorable traits over successive generations.