The continuously rising number of mobile users and applications drives spectrum scarcity. WiFi connectivity can help to reduce the load on cellular networks in urban areas for slow moving commuters if supported by adequate network management. This research explores reinforcement learning using context and network data to deal with the stochastic and dynamic nature of WiFi and provide continuous connectivity to a moving vehicle. We formulate the access point handoff problem as a Markov Decision Process (MDP) and solve it using Deep Q Network (DQN) applied to a real-world dataset. The observed pattern of learning in preliminary results indicates that the agent can learn from the real world dataset.