To improve the user experience, personalization is growing more essential as in-car infotainment methods progress. To provide a personalized driving experience, this paper investigates a personalized in-car infotainment system that combines Reinforcement Learning (RL) with Internet of Things (IoT) technology. Using IoT sensors to gather current information of driver preferences, vehicle conditions, and external variables. Following this data processing, the RL algorithm optimizes the user experience by adjusting the infotainment elements, such as media playing, navigation routes, and temperature control. The RL model is built to learn from interactions and feedback in real so it can adapt to the driver's changing tastes and provide better recommendations over time. This method keeps the system responsive and flexible over time, making the in-car experience more personalized. Details of the system's design, data flow, and implementation, such as the RL model's design and its connection with IoT components, are detailed in the paper. Evaluations show that the technology works as advertised, making driving easier and more comfortable. It showcases the potential of RL, an AI method, to transform in-car infotainment systems into smart and flexible environments. © 2025 Elsevier B.V., All rights reserved.