A method of scheduling packets belonging to a plurality of data flow categories in a multi-access telecommunication system sharing a plurality of transmission resources. The method includes at each transmission time interval the selection, by a scheduler (CT, CF) of a resource allocation plan and an allocation of the transmission resources to the data streams in accordance with the selected resource allocation plan. This selection is performed by querying a correspondence table (LUT) whose content results from the implementation of reinforcement learning and which makes it possible to identify, from the current state of the multi-party telecommunications system, access (s [t]]), the resource allocation plan to be selected, this plan being optimal to satisfy heterogeneous needs in terms of quality of service.
展开▼