A controller for controlling an entity is provided. The controller comprises a memory to store a hierarchical multimodal reinforcement learning (RL) neural network, and a processor. The hierarchical multimodal RL neural network includes a first level controller and two second level controllers. Each of the second level controllers comprise a first sub level controller relating to a first modality and a second sub level controller relating to a second modality. The first modality is different from the second modality. The processor is configured to select one of the two second level controllers to perform a first sub-task relating to a task, using the first level controller, based on input data and a state of the hierarchical multimodal RL neural network. The selected second level controller is configured to determine a set of control actions to perform the first sub-task, and control the entity based on the set of control actions.

A method for associating user equipment with base stations of a cellular network such as a 5G network. An agent receives an observation of its environment and deduces an action therefrom, this action being manifested as an association request of the user to a neighboring base station. This action is chosen according to a strategy of the user seeking the maximum of a function of action value for the observation and several possible actions. Once the actions have been carried out by the various actions, a common reward is provided by the network to the various users, the latter being zero in the case of a collision of association requests and the result of a utility function otherwise. The function of action value for the various possible actions is predicted by a recurrent neural network trained on a set of experiments stored in a local memory.

A robot device controller including a memory configured to store a statistical model trained to implement a behaviour of the robot device, one or more processors configured to determine a nominal trajectory represented by the statistical model, determine an expected force experienced by the robot device when the robot device is controlled to move in accordance with the nominal trajectory, determine a measured force experienced by the robot device when the robot device is controlled to move in accordance with the nominal trajectory and adapt the statistical model based on a reduction of the difference between the measured force and the expected force.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via scene-based editing using image understanding facilitated by artificial intelligence. For example, in one or more embodiments the disclosed systems utilize generative machine learning models to create modified digital images portraying human subjects. In particular, the disclosed systems generate modified digital images by performing infill modifications to complete a digital image or human inpainting for portions of a digital image that portrays a human. Moreover, in some embodiments, the disclosed systems perform reposing of subjects portrayed within a digital image to generate modified digital images. In addition, the disclosed systems in some embodiments perform facial expression transfer and facial expression animations to generate modified digital images or animations.