Reinforcement learning based radio resource scheduling in LTE-advanced

In this paper, a novel radio resource scheduling policy for Long Term Evolution Advanced (LTE-A) radio access technology in downlink acceptance is proposed. The scheduling process works with dispatching rules which are various with different behaviors. In the literature, the scheduling disciplines are applied for the entire transmission sessions and the scheduler performance strongly depends on the exploited discipline. Our method provides a straightforward schedule within transmission time interval (TTI) frame. Hence, a mixture of disciplines can be used for each TTI instead of the single one adopted across the whole transmission. The grand objective is to bring real improvements in terms of system throughput, system capacity and spectral efficiency (operator benefit) assuring in the same time the best user fairness and Quality of Services (QoS) capabilities (user benefit). In order to meet this objective, each rule must to be called on the best matching conditions. The policy adoption and refinement are the best way to optimize the use of mixture of rules. The Q-III reinforcement learning algorithm is proposed for the policy adoption in order to transform the scheduling experiences into a permanent nature, facilitating the decision-making on which rules will be used for each TTI. The IQ-III reinforcement learning algorithm using multi-agent environments refines the policy adoption by considering the agents' opinions in order to reduce the policy convergence time.