The use of cognitive multidisciplinary strategies represents a powerful tool to allow a communication system to transmit and receive data in a secure way by working in parallel with other electromagnetic devices, sharing the same frequency channels, without being affected by malfunctions caused by unintentional or intentional interferences (e.g. jammers). The cognitive operation is possible by modeling the channel behavior and predicting future channel occupancy. The model of the electromagnetic environment is based on the observation of the spectrum occupancy over time and on suitable reinforced learning strategies to acquire the characteristics of the channel occupancy. The learning operation is paramount, as the prediction about channel occupancy is possible only after understanding the behavior of the concurrent emitters present in the scenario. This paper describes the concept of reinforced learning techniques, based on emitter classification and matching and on human in the loop agent. implemented on a number of real cases of emitter behavior. We show that, in selected study cases, our reinforced learning techniques based on cognitive multidisciplinary strategies can provide good performance, even in presence of a consistent number of concurrent transmitters.