Energy management in electric vehicles plays a significant role in both reducing energy consumption and limiting the rate of battery capacity degradation. The work summarized in this paper explores machine-learning techniques for electrified propulsion control in designing energy management (EM) controllers. The role of the EM is to coordinate delivery of multiple power requests from a modular battery of an electric vehicle (EV) to improve range and battery longevity. Reinforcement learning is adopted for integrated EV traction and HVAC controls. The EM acts as a supervisory controller augmenting the HVAC controls. It is designed to adjust internal HVAC control parameters based on current drive parameters to improve energy efficiency and battery state of health (SoH) without affecting driver demand and cabin comfort. An empirical battery aging model is incorporated into the problem formulation to address long-term battery capacity degradation. Reduced energy consumption and battery aging are demonstrated.