Partially Cooperative RL for Hybrid Action CRNs With Imperfect CSI

Cognitive radio networks (CRNs) mitigate spectrum scarcity by leveraging the holes in the licensed spectrum to enable Internet of Things (IoT) devices to opportunistically access the spectrum. However, IoT devices need to sense the spectrum before they can access it, which is an energy-intensive process and hinders the practical implementation of opportunistic spectrum access for energy-constrained IoT devices. In this context, reinforcement learning-based algorithms that encourage cooperation among IoT devices to eliminate the need for constant sensing are promising candidates for practical CRN implementation. As exciting as the application of reinforcement learning to CRNs is, benchmarking the performance of different algorithms is a huge challenge due to a lack of standardized comparison metrics, especially for hybrid action spaces that comprise both discrete and continuous actions. We propose a hybrid discrete-continuous space deep reinforcement learning algorithm that maximizes the energy efficiency of CRNs by optimizing sensing, cooperation, and transmission by IoT devices. We also analyze the algorithm’s performance by setting the theoretical upper bound for throughput and find that it reaches 99.4% of the theoretical upper bound, while its discrete action-space version reaches 96% and other baseline algorithms range between 70% and 86%.