US Patent Issued to NVIDIA on March 3 for "Method for fast and better tree search for reinforcement learning" (Israeli, American, Italian Inventors)

ALEXANDRIA, Va., March 3 -- United States Patent no. 12,566,801, issued on March 3, was assigned to NVIDIA Corp. (Santa Clara, Calif.).

"Method for fast and better tree search for reinforcement learning" was invented by Shie Mannor (Haifa, Israel), Assaf Joseph Hallak (Tel Aviv, Israel), Gal Dalal (Haifa, Israel), Steven Tarence Dalton (Cary, N.C.), Iuri Frosio (Bergamo, Italy) and Gal Chechik (Ramat Hasharon, Israel).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method for performing a Tree-Search (TS) on an environment is provided. The method comprises generating a tree for a current state of the environment based on a TS policy, determining a corrected TS policy, and determining an action to apply to th...