5G networks will grant spectacular improvements of the most relevant Key Performance Indicators (KPIs) while allowing resource multi-tenancy through network slicing. However, the other side of the coin is represented by the huge increase of the management complexity and the need for efficient algorithms for resource orchestration. Therefore, the management and orchestration of the network through Artificial Intelligence (AI) and Machine Learning (ML) algorithms is considered a promising solution, as it allows to reduce the human interaction (usually expensive and error-prone) and scale to large scenario composed by thousands of slices in heterogeneous environments. In this paper, we provide a review of the current standardization efforts in this field, mostly due to the work performed by the Experiential Network Intelligence (ENI) industry specification group (ISG) within the European Telecommunications Standards Institute (ETSI). Then, we thoroughly describe an exemplary use case on elastic network management and orchestration through learning solutions proposed by the 5GPPP project 5G-MoNArch and recently approved at ETSI ENI.