Abstract: Disclosed are systems and methods for training at least one policy using a framework for encoding human behaviors and preferences in a driving environment. In one example, the method includes the steps of setting parameters of rewards and a Markov Decision Process (MDP) of the at least one policy that models a simulated human driver of a simulated vehicle and an adaptive human-machine interface (HMI) system configured to interact with each other and training the at least one policy to maximize a total reward based on the parameters of the rewards of the at least one policy.

Abstract: A jewelry device having interchangeable ornaments is provided. A main base of the device has a recess adapted to receive a removable ornament. The main base has a flange formed on an interior of the top side within the recess. The flange retains an ornament and prevents it from falling out of the top of the device. A securing door is attached to the bottom side of the main base. The securing door has a top side facing the recess and a bottom side opposite the top side. The securing door is movable between a closed position substantially in contact with the main base and an open position. A leaf spring is attached to the top side of the securing door. The spring is adapted to bias against a removable ornament disposed in the recess when the securing door is in the closed position and thus prevent it from rattling, becoming misaligned, or falling out. The device also contemplates the use of multiple ornamental inserts for disposal within the recess of the main base.