ALEXANDRIA, Va., April 7 -- United States Patent no. 12,596,955, issued on April 7, was assigned to HITACHI LTD. (Tokyo).

"Reward feedback for learning control policies using natural language and vision data" was invented by Andrew James Walker (Santa Clara, Calif.) and Joydeep Acharya (Milpitas, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Example implementations described herein involve systems and methods for providing a reward to a machine learning algorithm, which can include receiving an image, and a task description defined in text; slicing the image into a plurality of sub-images; executing an embedding model to embed the text of the task description and the sub-images to generate a distribu...