Abstract
Recommender Systems for the IoT (RSIoT) aim for interactive item recommendations. Most existing methods focus on user feedback and have limitations in dealing with dynamic environments. Deep Reinforcement Learning (DRL) can deal with dynamic environments and conduct updates without waiting for user feedback. In this study, we design a Reminder Care System (RCS) to harness the advantages of deep reinforcement learning in addressing two main issues of RSIoT: capturing dynamicity patterns of human activities and system update without a focus on user feedback. The RCS is formulated based on a Deep Q-Network (DQN), which works well with the dynamic nature of human activities. We further consider harvesting the feedback automatically in the back end without requiring users to explicitly label activities. Experiments are conducted on three public datasets and have demonstrated the performance of our proposed system.