Reinforcement Learning for Call Admission Control and Routing In Integrated Service Networks

Abstract:
In integrated service communication networks, an important problem is to excercise call admission control and routing so as to optimally use the network resources. This problem is naturally formulated as a dynamic programming problem, which, however, is too complex to be solved exactly. We use methods of reinforcement learning (RL), together with a decomposition approach, to find call admission control and routing policies. The performance of our policy for a network with approximately 10 ⁴⁵ states is compared with a commonly used heuristic policy.