Towards a multi-agent reinforcement learning approach for joint sensing and sharing in cognitive radio networks

The adoption of the Fifth Generation (5G) and beyond 5G networks is driving demand for learning approaches that enable users to co-exist harmoniously in a multi-user distributed environment. Although resource-constrained, Cognitive Radio (CR) has been identified as key enabler due its cognitive abilities ability access idle spectrum opportunistically. Reinforcement well suited meet because it does not require agent have prior information about environment which operates. Intuitively, CRs should be enabled implement reinforcement efficiently gain opportunistic with each other. However, application straightforward single-agent complex resource intensive multi-agent multi-objective In this paper, (1) we present brief history overview limitations; (2) provide review recent methods proposed algorithms applied networks; (3) further novel framework multi-CR conclude synopsis future research directions recommendations.