Effective climate control in Battery Electric Vehicles (BEVs) significantly impacts energy efficiency and passenger comfort. In heavy-duty electric vehicles, maintaining optimal cabin conditions becomes particularly challenging due to prolonged cabin occupancy, including overnight stays (hotel function). This introduces additional challenges in balancing temperature, relative humidity, and CO₂ levels with overall energy consumption. Model Predictive Control (MPC) and Reinforcement Learning (RL) are two advanced methods that can address these complex requirements. However, it remains unclear which strategy is more effective, or if integrating both could yield better results. This study investigates and compares MPC and RL control strategies for cabin climate management in heavy-duty BEVs. Using a detailed simulation model developed in MATLAB/Simulink within the ESCALATE EU-Research Project, specific use cases are tested to evaluate each strategy’s effectiveness at maintaining optimal cabin conditions while minimizing energy consumption under extended occupancy conditions. The results highlight key advantages and limitations of both approaches and explore potential synergies, providing insights for developing hybrid, adaptive control systems. Ultimately, this research aims to advance intelligent, energy-efficient, and comfort-oriented climate control solutions tailored specifically for heavy-duty electric vehicles.