Large volumes of data are becoming available with the growth of the advanced metering infrastructure. These are expected to benefit planning and operation of the future smart grid, and to help the customers transition from a passive to an active and dynamic player. In this research, we explore a novel approach in the smart grid context the benefits of using Deep Reinforcement Learning, a hybrid type of methods that combines Reinforcement Learning with Deep Learning, to perform real time optimization of schedules for smart energy management systems. The learning procedure was explored using Deep Q-learning and Deep Policy Gradient, both of them being extended to perform multiple actions simultaneously. The proposed approach was validated on the large-scale Pecan Street Inc. database. The Pecan database contains highly-dimensional information about photovoltaic power generation, electric vehicles as well as buildings appliances. Moreover, these on-line energy scheduling strategies could be used to provide real time advise and automatic actions for customers and prosumers to encourage more efficient use of electricity.