US Patent Issued to Google on Oct. 27 for "Deep reinforcement learning for robotic manipulation" (California, Massachusetts, New Jersey Inventors)

ALEXANDRIA, Va., Oct. 27 -- United States Patent no. 12,773,776, issued on Oct. 27, was assigned to Google LLC (Mountain View, Calif.).

"Deep reinforcement learning for robotic manipulation" was invented by Dmitry Kalashnikov (Fair Lawn, N.J.), Alexander Irpan (Palo Alto, Calif.), Peter Pastor Sampedro (Oakland, Calif.), Julian Ibarz (Mountain View, Calif.), Alexander Herzog (San Jose, Calif.), Eric Jang (Cupertino, Calif.), Deirdre Quillen (Brookline, Mass.), Ethan Holly (San Francisco) and Sergey Levine (Berkeley, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Using large-scale reinforcement learning to train a policy model that can be utilized by a robot in performing a robotic task in which the ro...