AN ACTOR-CRITIC REINFORCEMENT LEARNING APPROACH TO MINIMUM AGE OF INFORMATION SCHEDULING IN ENERGY HARVESTING NETWORKS

We study age of information (AoI) minimization in a network consisting of energy harvesting transmitters that are scheduled to send status updates to their intended receivers. We consider the user scheduling problem over a communication session. To solve online user scheduling with causal knowledge of the system state, we formulate an infinite-state Markov decision problem and adopt model-free on-policy deep reinforcement learning (DRL), where the actor-critic algorithm with deep neural network function approximation is implemented. Comparable AoI to the offline optimal is demonstrated, verifying the efficacy of learning for AoI-focused scheduling and resource allocation problems in wireless networks.