US Patent Issued to Intuit on April 21 for "Replay buffer integration for group-based relative policy optimization in machine learning" (Israeli Inventors)

ALEXANDRIA, Va., April 21 -- United States Patent no. 12,608,622, issued on April 21, was assigned to Intuit Inc. (Mountain View, Calif.).

"Replay buffer integration for group-based relative policy optimization in machine learning" was invented by Shirli Dicastro (Kfar Saba, Israel), Shai Ardazi (Petah Tikva, Israel), Ofir Ben Shoham (Hod Hasharon, Israel) and Gidi Zilbar (Ein Shemer, Israel).

According to the abstract* released by the U.S. Patent & Trademark Office: "Aspects of the present disclosure provide techniques for optimizing a policy model in a reinforcement learning framework, involving generating output completions for an input query, evaluating the output completions with a reward model, and storing related data in a replay b...