The adoption of electric vehicles (EVs) by transportation network company (TNC) drivers has the potential to reduce emissions and increase energy efficiency in the transportation sector, but the limited range of EVs creates usability challenges for drivers. When deciding when and where to charge their vehicles, drivers must consider many evolving and uncertain factors, including the destinations of future trips, current traffic conditions, the occupancy of vehicle-charging stations, and the cost of energy. This study has explored the feasibility of using deep reinforcement learning (DRL) techniques to optimize the charging behavior of EVs that are driven for TNCs such as Lyft and Uber. We used DRL to learn to estimate an optimal strategy in the form of an artificial neural network, which can be used as an onboard decision-support tool that recommends when and where to charge an EV based on the multidimensional state of local transportation and energy systems, as well as driver objectives. We show that such a support tool could help reduce the energy costs and emissions of a TNC EV while providing a similar level of transportation services. We developed an agent-based simulation environment incorporating models of transportation systems and power grids for training and testing EV driving and charging strategies and demonstrated the feasibility of using a trained EV charging strategy to reduce carbon footprint and cost per driven mile. Our experiments show a reduction of costs per mile by ~16% for individual cars which would have a potential savings impact of ~US$0.9B on today?s ride-hailing industry. This study supports the objectives of the DOE Vehicle Technologies Office?s Energy Efficient Mobility Systems program by demonstrating a technology that can increase the energy efficiency of new mobility services and brings more arguments for the adoption of EVs by commercial mobility services to improve their performance and usability.