Abstract: A rational inattention reinforcement learning (RIRL) framework determines actions of actors based on observations while modeling human irrationality or rational inattention. The RIRL framework decomposes observations into a set of observations, and passes the set through multiple information channels modeled as encoders having different information costs. Discriminators of the encoders measure a cost of mutual information (MI) associated with the observations. A stochastic action module of the RIRL framework receives encodings of the encoders and a history of encoded information from a previous iteration, and generates a distribution of actions. The stochastic action module includes a discriminator for measuring a cost of MI associated with the stochastic action module. The RIRL framework computes a reward based on the cost of MI of stochastic encoders, the cost of MI of the stochastic action module, and the distribution of actions. From the reward, the actions of the actors are determined.

Abstract: Systems and methods for sequential recommendation are described. Embodiments receive a user interaction history including interactions of a user with a plurality of items, select a constraint from a plurality of candidate constraints based on lifetime values observed for the candidate constraints, wherein the lifetime values are based on items predicted for other users using a recommendation network subject to the candidate constraints, and predict a next item for the user based on the user interaction history using the recommendation network subject to the selected constraint.

Abstract: Systems and methods for a steering a vehicle. In one example, a system includes a first wheel, a second wheel, and a skid/differential steering system including an electronic processor. The electronic processor is configured to receive, from an electronic power steering system, a steering failure signal and a target steering angle, determine, based on the target steering angle, a target yaw rate, and drive the first wheel of the vehicle forward and decelerate the second wheel of the vehicle based on the target yaw rate, turning the vehicle.

Abstract: A vehicle having an autonomous function that can initiate an active-stop mode in the event that a driver-takeover mode is not successfully completed in response to detecting a condition warranting driver takeover from the autonomous function. In some embodiments, an emergency-stop mode may override the driver-takeover mode or the active-stop mode in response to detection of a condition warranting an emergency stop.