Finding Optimal Policy for Queueing Models: New Parameterization
This work addresses queueing control in applications like communication networks, but it appears incremental as it builds on existing reinforcement learning frameworks with a novel parameterization.
The authors tackled the problem of learning optimal policies for queueing systems by proposing a new policy parameterization based on intrinsic network properties, achieving good performance across various traffic loads.
Queueing systems appear in many important real-life applications including communication networks, transportation and manufacturing systems. Reinforcement learning (RL) framework is a suitable model for the queueing control problem where the underlying dynamics are usually unknown and the agent receives little information from the environment to navigate. In this work, we investigate the optimization aspects of the queueing model as a RL environment and provide insight to learn the optimal policy efficiently. We propose a new parameterization of the policy by using the intrinsic properties of queueing network systems. Experiments show good performance of our methods with various load conditions from light to heavy traffic.