Spending an uncontrolled quantity and quality of time on digital news and social media platforms can negatively influence mental health and decrease cognitive abilities. In this paper, we propose a sequential news recommendation system employing deep reinforcement learning to capture the user’s short and long-term interests while blending social news with micro-learning informative news items that can help users derive useful outcomes out of their online presence. In the absence of a publicly available dataset, we developed a simulation model to synthesize data and evaluate the proposed news recommendation system. We train and evaluate our model on synthesized data and show an improvement in user satisfaction.