ALEXANDRIA, Va., Sept. 30 -- United States Patent no. 12,430,564, issued on Sept. 30, was assigned to NVIDIA Corp. (Santa Clara, Calif.).
"Fine-tuning policies to facilitate chaining" was invented by Yuke Zhu (Austin, Texas), Anima Anandkumar (Pasadena, Calif.) and Youngwoon Lee (Los Angeles).
According to the abstract* released by the U.S. Patent & Trademark Office: "A manipulation task may include operations performed by one or more manipulation entities on one or more objects. This manipulation task may be broken down into a plurality of sequential sub-tasks (policies). These policies may be fine-tuned so that a terminal state distribution of a given policy matches an initial state distribution of another policy that immediately follow...