Minimizing the Age-of-Critical-Information: An Imitation Learning-Based Scheduling Approach Under Partial Observations

Recently, Age of Information (AoI) has become an important metric to evaluate the freshness of information, and studies on minimizing AoI in wireless networks have drawn extensive attention. In mobile edge networks, the change of critical levels for distinct information is important for users’ decision making, especially when merely partial observations are available. However, existing researches have not addressed that issue yet. To tackle the above challenges, we first establish the system model, in which the information freshness is quantified by the changes of its critical levels. We formulate the Age-of-Critical-Information (AoCI) minimization issue as an optimization problem, with the purpose of minimizing the average relative AoCI of mobile clients to help them make timely decisions. Then, we propose an information-aware heuristic algorithm that can reach optimal performance with full obsevations in an offline manner. For online scheduling, an imitation learning-based scheduling approach is designed to decide update preferences for mobile clients under partial observations, where policies obtained by the above heuristic algorithm are utilized for expert policies. At last, we demonstrate the superiority of our designed algorithm from both theoretical and experimental perspectives.