Sleep analysis is considered as an important process in sleep disorders identification and highly dependent of sleep scoring. Sleep scoring is a complex, time consuming and exhausting task for experts. In this paper, we propose an automatic sleep scoring model based on unsupervised learning to avoid the pre-labeling task. Taking advantage of the distributed nature of Multi-agent Systems (MAS), we propose a classification model based on various physiological signals coming from heterogeneous sources. The proposed model offers a totally cooperative learning to automatically score sleep into several stages based on unlabeled data. The existing heterogeneous adaptive agents are dealing with a dynamic environment of various physiological signals. The efficiency of our approach was investigated using real data. Promising results were reached according to a comparative study carried out with the often used classification models. The generic proposed model could be used in fields where data are coming from heterogeneous sources and classification rules are not predefined.